SlideShare a Scribd company logo
Streetwise
Machine Learning
for Painless Parking
Christopher R. Dance
Plan
1. Parking data context
2. Pricing
3. Sampling
1.
Parking Data
1. Parking Data
What?
mobile cameras, cell phonespolicies, mapsin-street sensors
traffic flow special events, …satellites (pollution) surveys
payments, violations
1. Parking Data
Why?
Use cases
1. set parking policy: prices, demarcation, …
2. guide enforcement officers to offenders
3. guide drivers to the best vacancies
Value
1. less time wasted finding a space
2. less pollution, better health
3. access to local businesses
4. fair-and-transparent
Challenge
maximise the utility (value minus cost) of the data
1. Parking Data
Who?
Many cities have deployed smart parking systems since 2010
San Francisco, London, Moscow, …
Our contributions
Since 2012, we have deployed 6 new technologies in 3 major cities
Los Angeles. Basic pricing method, time-of-week subdivision, real-time pricing as
rate, optimal learning while selling, surveys, effectiveness evaluation, non-payment
evaluation (and not deployed: real-time parking guidance, real-time pricing as integral)
Washington DC. Spatiotemporal sampling: sensor allocation and reconstruction,
spatial queueing for demarcation decisions
Berkeley. Fusion of temporal sampling with payment data
Awards for this work included ITS Innovation, IPI Innovation and MIT Top-50
2.
Pricing
Zoeter et al , New Algorithms for Parking Demand Management. Proc. 20th ACM KDD, 2014
Glasnapp et al, Understanding Dynamic Pricing for Parking in Los Angeles. Intl. Conf. HCI in Business, 2014
2. Pricing
Context. Demand-Based Pricing
2. Pricing
Problem
Learn on-street parking prices to make the city happier
⇒ maximize the rate at which people get value from the system (not revenue)
Challenges
1. Model or forecast for value when driver behavior varies in 5 dimensions
frequency, location, arrival, duration, legality-fraction
2. Ensure simplicity so drivers remember and city official can explain
in the face of huge variations in demand in space and time
3. How big should price increments be?
too large ⇒ prices might oscillate from month-to-month
too small ⇒ system may have no useful effect
2. Pricing
Model for Value
Goal. Choose appropriate reward function
If more people are parked, then
• more people get value
• but the distance to a space increases
For a geometric distribution of vacancies
distance to a space =
𝑓
1−𝑓
where the occupancy fraction is 𝑓
But this is singular as 𝑓 → 1!
occupancy fraction
mean spaces to first vacancy
- geometric distribution
2. Pricing
Distance to a Space
The singularity is unrealistic as occupancy
fractions vary spatially
spatial autocorrelation of
occupancy fraction (LA 2012 data)
mean spaces to first vacancy
- geometric distribution
- real data
occupancy fraction
2. Pricing
Simple Valuation Model
occupancy fraction
Gradient Ascent
Move up the gradient of the total valuation
w.r.t. price 𝒑, so
new-price – old-price
∼
𝝏
𝝏𝒑
‫׬‬𝓡
valuation−rate 𝒑, 𝒕, 𝒙 𝒅𝒙 𝒅𝒕
⇒ simple for machine-learning scientists,
but NOT for citizens and officials...
valuation rate (per space, per unit time)
= constant per person parked
- k × distance travelled per arrival
2. Pricing
Simple Valuation Model
occupancy fraction
⇒ simple for machine-learning scientists,
but NOT for citizens and officials…
valuation rate (per space, per unit time)
= constant per person parked
- k × distance travelled per arrival
Towards a simpler rule
Maximizing the black curve is nearly the
same as maximizing the red curve, whose
gradients are -1, 0 or 1
approximation
Gradient Ascent
Move up the gradient of the total valuation
w.r.t. price 𝒑, so
new-price – old-price
∼
𝝏
𝝏𝒑
‫׬‬𝓡
valuation−rate 𝒑, 𝒕, 𝒙 𝒅𝒙 𝒅𝒕
2. Pricing
Voting Rule
Voting Rule
If 𝑯 − 𝑳 > 0.3 then increase the price
If 𝑳 − 𝑯 > 0.3 then decrease the price
Prices are on a ladder $0.5, $1, $1.50, $2, $3, …, $7 per hour
Definition
The high vote, 𝑯, is the fraction of time that the system is over 90% occupied
The low vote, 𝑳, is the fraction of time that the system is under 70% occupied
2. Pricing (A Tale of Two Cities)
Comparison
Average Occupancy Rule (used in San Francisco)
If average occupancy fraction > 𝟎. 𝟖 then increase the price by $0.25
If average occupancy fraction < 𝟎. 𝟔 then decrease the price by $0.25
average occupancy fraction 0.67 0.67
average occupancy rule price same price same
voting rule price down price up
mean distance to vacancy 2 spaces 11 spaces
occupancy
fraction
Scenario A Scenario B
2. Pricing - How did prices ($/HR) change?
Area is proportional to the sum over spaces of the
number of hours at the given price
Before (1st June 2012) After (1st January 2013)
$5
$4
$3
$2
$150
$1
$050
$4
$3
$2
$1
50% of prices decreased
yet revenue increased by 12%
2. Pricing
Does it work?
Price increase from $4/hour to $5/hour
No vacancy = full (red)
More availability (yellow and green)
Occupancy time series for 701 South Olive Street, one row = one weekday (Mon-Fri not Sat-Sun)
Underused (blue)
… but is this
• the impact of the price change
• a change in sensor signal-processing
• a lucky coincidence
• something else?
March-June 2012
June-December 2012
2. Pricing
Does it work?
# congested spaces
(≥ 18 of closest neighbours occupied)
11AM Noon 1PM 2PM 3PM 4PM
300
400
500
600
700
800
900
1000
1100
1200
1300
11AM Noon 1PM 2PM 3PM 4PM
2800
3000
3200
3400
3600
3800
4000
4200
4400
4600
4800
# under-used spaces
(≤ 14 of closest neighbours occupied)
10% reduction 5% reduction
Handicapped placards
• 80% of parking in highly-congested areas now goes for free to handicapped placard users
• Maybe, many such drivers use placards illegally
• Law-changing takes time, but is ongoing
Minimum price
• The minimum acceptable price ($0.5 per hour) was already reached in under-used areas
• But occupancy there has continued to increase substantially
• It’s hard to distinguish between economic improvement and long-term price-change latency
Political acceptance
Unlike SFPark, LA ExpressPark receives positive press coverage and continues to expand today
Clinchant et al, Using Analytics to Understand On-Street Parking. Proc. 22nd World Congress on ITS, 2015
2. Pricing
Does it work? Results for 2013-16
3.
Sampling
3. Sampling
Motivation
Solutions
1. Spatial sampling:
don’t observe all stalls
2. Temporal sampling:
don’t observe all the time
Deployed in Washington DC and
Berkeley
Problem
LA’s sensors are too
expensive. Can we
combine sensing
methods to ensure high-
quality data while saving
90% of the costs?
Dance, Lean Smart Parking. The Parking Professional, vol. 30, no. 6, 2014
3. Sampling
Problem P1
Informally
Given
• a normally-distributed discrete-time time-series
• noisy measurements that come at a cost
Question
When should you measure so as to minimise the cost
of prediction errors plus measurement costs?
black = true time-series (unobserved)
red = forecast standard-deviation
blue = costly measurements
Formally
Time-series
𝑿 𝒕+𝟏 = 𝑨𝑿 𝒕 + 𝑵(𝟎, 𝑸)
Actions
𝑎 𝑡 = 1 for good measurement, cost 𝑐
𝑎 𝑡 = 0 for poor measurement, no cost
Measurements
𝒀 𝒕 = 𝑩𝑿 𝒕 + 𝑵 𝟎, 𝑹(𝒂 𝒕)
History
𝐻𝑡 = (𝑎1, 𝑎2, … , 𝑎 𝑡−1, 𝒀 𝟏, 𝒀 𝟐, … , 𝒀𝒕−𝟏)
Policy
𝑎 𝑡 = 𝜋(𝐻𝑡)
Forecasts
෡𝑿 𝒕 = 𝐄 𝑿 𝒕 𝐻𝑡] given by the Kalman filter
Objective
min
𝜋
𝐄 σ 𝑡=1
∞
𝛾 𝑡 ෡𝑿 𝒕 − 𝑿 𝒕
2
+ 𝑐 𝑎 𝑡
time
3. Sampling
Problem P1: Examples
Parking
time-series occupancy of a block face
measurements from mobile cameras and payment data
Military
time-series position of a submarine
measurements by sonar
Telecommunications
time-series position of a handset
measurements with 5G antenna
3. Sampling
Problem P1: Related Work
P1 addresses the basic machine learning trade-off between
• the cost of data acquisition
• the cost of errors due to a lack of data
in a particularly simple way
If we solve P1, then we also solve
• “the LQG control problem with costly measurements”(Meier et al, 1967)
The continuous-time version of this problem was solved only recently (Le Ny et al, 2011)
Niño-Mora and Villar (2009) conjectured that an optimal policy for P1 is a threshold policy
• i.e. measure if and only if the posterior variance exceeds a threshold.
Meier et al, Optimal control of measurement subsystems. IEEE TAC, 1967
Le Ny et al, Scheduling continuous-time Kalman filters. IEEE TAC, 2011
Niño-Mora and Villar, Multi-target tracking via restless bandit marginal productivity indices. IEEE CDC, 2009
3. Sampling
Attention Mechanism Problem
Street 1
Street 2
Street 3
observation times
Given
• 𝑛 time-series to track, as in P1
• with 𝑚 sensors, where 𝑚 < 𝑛
Question
Which time-series should you measure at each time, so
as to minimise the total prediction error?
Discussion
• This problem has state space ℝ 𝑛
and 𝑛
𝑚
actions!
• Nevertheless, Whittle (1988) proposed a
computationally-efficient policy for this problem for
large 𝑚, 𝑛
• But to compute that policy, we must first solve P1
Example
• 4 cameras observing 800 streets in
Washington DC
• This was our original motivation for
this work
Whittle, Restless bandits: activity allocation in a changing world. J. App. Prob., 1988
3. Sampling
Attention Mechanism Problem
Claim. Assuming P1 is solved, Whittle’s policy does much better than other heuristics
Example. 10 time-series, 1 sensor, weights on predictive variance 𝑤1 = 40, 𝑤2:10 = 1
time-series
time, 𝑡
colour = weighted
prediction error
Myopic policy
Observes the time-series
with the largest weighted
predictive variance
(often used in radar tracking)
Round-robin policy
Observes time-series 1, 2,
…, 10, 1, 2, …, 10, …
Whittle’s policy
3. Sampling
Solution to P1
Dance and Silander, When are Kalman-Filter Restless Bandits Indexable? NIPS, 2015
Dance and Silander, Optimal Policies for Observing Time Series, in review, JMLR, 2017 (see arXiv)
Theorem (Dance and Silander, 2017)
1. A threshold policy is optimal for Problem P1
2. This result holds for many cost functions
minimum predictive variance,
minimum predictive entropy,
maximum predictive precision, …
3. There is a simple polynomial-time algorithm for approximating the threshold
3. Sampling
Key to the proof
Examine the behaviour of the system under a
threshold policy
• The state 𝑥𝑡 is given by the predictive variance
• Its dynamics are given by the Kalman filter
variance updates, which are nonlinear
𝜙0 - no measurement (below threshold)
𝜙1 - measurement made (above threshold)
• So, for threshold 𝑧 we have
𝑥𝑡+1 = 𝑓 𝑥𝑡; 𝑧 ≔ ቊ
𝜙0(𝑥𝑡), 𝑥𝑡 < 𝑧
𝜙1(𝑥𝑡), 𝑥𝑡 ≥ 𝑧
action 0 action 1
threshold
3. Sampling
Insights: Maps-with-Gaps
The behaviour of iterated function systems
𝑥𝑡+1 = 𝑓(𝑥𝑡)
has been extensively studied when 𝑓 is smooth
But our 𝑓(⋅; 𝑧) is discontinuous
Such maps-with-gaps are also important as models of:
• switching in electrical circuits
• neural spiking behaviour
• gene regulatory networks, …
3. Sampling
Insights: Words
How does the action sequence generated by our
map change
• as we vary the threshold 𝑧
• from initial state 𝑥1 = 𝑧?
The action sequence is an infinite word on the
alphabet {0,1}
Question
What types of word does our map generate?
time,𝑡
threshold, 𝑧
black = action 0
white = action 1
3. Sampling
Answer: Mechanical Words
Definition
A mechanical word is an infinite binary string whose 𝑛th letter is
𝑤 𝑛 = 𝑎(𝑛 + 1) − 𝑎𝑛 for some 𝑎 in [0,1].
Examples
𝑎 = 1/2 ⇒ the word 01 01 01 01…
𝑎 = 3/7 ⇒ the word 00100101 00100101 00100101…
Mechanical words correspond to the slopes of digital straight lines
Relation to the literature
• Kozyakin (2003) found general conditions under which nonlinear maps-with-gaps generate
mechanical words
• However, the relationship between the choice of threshold and the word generated was only
discovered for linear maps-with-gaps by Rajpathak et al (2012)
• Our work extends this threshold-to-word relationship to nonlinear maps
0 0
0 0
0
1
1
1
Kozyakin, Sturmian sequences generated by order-preserving circle maps. Inst. Information Trans., RAS, 2003
Rajpathak et al, Analysis of stable periodic orbits in the one-dimensional linear discontinuous map. Chaos, 2012
3. Sampling
Open Questions
• What happens if there are more than 2 types of measurements?
• What can be said in the multivariate Gaussian case?
• What about non-Gaussian time-series?
4.
Outlook
Outlook
1. Widespread adoption of demand-management technologies makes sense
2. Counting cars with computer vision seems most cost-effective
⇒ room for improvement in accuracy of on-street car counts
3. Forecasting non-demarcated parking remains challenging
4. Parking policy and guidance for autonomous vehicles
⇒ enable more effective mechanisms:
routing policies, reservations, options, lotteries, …
⇒ while making life simpler for citizens
Q & A
Thank you

More Related Content

What's hot

Bol.com
Bol.comBol.com
Bol.com
BigDataExpo
 
Notes from Coursera Deep Learning courses by Andrew Ng
Notes from Coursera Deep Learning courses by Andrew NgNotes from Coursera Deep Learning courses by Andrew Ng
Notes from Coursera Deep Learning courses by Andrew Ng
dataHacker. rs
 
Deep Learning for AI (3)
Deep Learning for AI (3)Deep Learning for AI (3)
Deep Learning for AI (3)
Dongheon Lee
 
Approximate "Now" is Better Than Accurate "Later"
Approximate "Now" is Better Than Accurate "Later"Approximate "Now" is Better Than Accurate "Later"
Approximate "Now" is Better Than Accurate "Later"
NUS-ISS
 
Neural Networks and Deep Learning for Physicists
Neural Networks and Deep Learning for PhysicistsNeural Networks and Deep Learning for Physicists
Neural Networks and Deep Learning for Physicists
Héloïse Nonne
 
Machine Learning for Everyone
Machine Learning for EveryoneMachine Learning for Everyone
Machine Learning for Everyone
Dhiana Deva
 
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
MLconf
 
Capitalico / Chart Pattern Matching in Financial Trading Using RNN
Capitalico / Chart Pattern Matching in Financial Trading Using RNNCapitalico / Chart Pattern Matching in Financial Trading Using RNN
Capitalico / Chart Pattern Matching in Financial Trading Using RNN
Alpaca
 
Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)
Alexander Korbonits
 
雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超
雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超
雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超
台灣資料科學年會
 
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
MLconf
 
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
Edge AI and Vision Alliance
 
20170406 Genomics@Google - KeyGene - Wageningen
20170406 Genomics@Google - KeyGene - Wageningen20170406 Genomics@Google - KeyGene - Wageningen
20170406 Genomics@Google - KeyGene - Wageningen
Allen Day, PhD
 
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
Aseda Owusua Addai-Deseh
 
QCon Rio - Machine Learning for Everyone
QCon Rio - Machine Learning for EveryoneQCon Rio - Machine Learning for Everyone
QCon Rio - Machine Learning for Everyone
Dhiana Deva
 
Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks
Applying Deep Learning to Enhance Momentum Trading Strategies in StocksApplying Deep Learning to Enhance Momentum Trading Strategies in Stocks
Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks
Lawrence Takeuchi
 
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Altoros
 
Josh Patterson MLconf slides
Josh Patterson MLconf slidesJosh Patterson MLconf slides
Josh Patterson MLconf slides
MLconf
 
Google Developer Groups Talk - TensorFlow
Google Developer Groups Talk - TensorFlowGoogle Developer Groups Talk - TensorFlow
Google Developer Groups Talk - TensorFlow
Harini Gunabalan
 
Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)
Oswald Campesato
 

What's hot (20)

Bol.com
Bol.comBol.com
Bol.com
 
Notes from Coursera Deep Learning courses by Andrew Ng
Notes from Coursera Deep Learning courses by Andrew NgNotes from Coursera Deep Learning courses by Andrew Ng
Notes from Coursera Deep Learning courses by Andrew Ng
 
Deep Learning for AI (3)
Deep Learning for AI (3)Deep Learning for AI (3)
Deep Learning for AI (3)
 
Approximate "Now" is Better Than Accurate "Later"
Approximate "Now" is Better Than Accurate "Later"Approximate "Now" is Better Than Accurate "Later"
Approximate "Now" is Better Than Accurate "Later"
 
Neural Networks and Deep Learning for Physicists
Neural Networks and Deep Learning for PhysicistsNeural Networks and Deep Learning for Physicists
Neural Networks and Deep Learning for Physicists
 
Machine Learning for Everyone
Machine Learning for EveryoneMachine Learning for Everyone
Machine Learning for Everyone
 
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
 
Capitalico / Chart Pattern Matching in Financial Trading Using RNN
Capitalico / Chart Pattern Matching in Financial Trading Using RNNCapitalico / Chart Pattern Matching in Financial Trading Using RNN
Capitalico / Chart Pattern Matching in Financial Trading Using RNN
 
Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)
 
雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超
雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超
雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超
 
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
 
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
“Introducing Machine Learning and How to Teach Machines to See,” a Presentati...
 
20170406 Genomics@Google - KeyGene - Wageningen
20170406 Genomics@Google - KeyGene - Wageningen20170406 Genomics@Google - KeyGene - Wageningen
20170406 Genomics@Google - KeyGene - Wageningen
 
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
Day 2 (Lecture 5): A Practitioner's Perspective on Building Machine Product i...
 
QCon Rio - Machine Learning for Everyone
QCon Rio - Machine Learning for EveryoneQCon Rio - Machine Learning for Everyone
QCon Rio - Machine Learning for Everyone
 
Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks
Applying Deep Learning to Enhance Momentum Trading Strategies in StocksApplying Deep Learning to Enhance Momentum Trading Strategies in Stocks
Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks
 
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
 
Josh Patterson MLconf slides
Josh Patterson MLconf slidesJosh Patterson MLconf slides
Josh Patterson MLconf slides
 
Google Developer Groups Talk - TensorFlow
Google Developer Groups Talk - TensorFlowGoogle Developer Groups Talk - TensorFlow
Google Developer Groups Talk - TensorFlow
 
Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)
 

Viewers also liked

[241]large scale search with polysemous codes
[241]large scale search with polysemous codes[241]large scale search with polysemous codes
[241]large scale search with polysemous codes
NAVER D2
 
[213]building ai to recreate our visual world
[213]building ai to recreate our visual world[213]building ai to recreate our visual world
[213]building ai to recreate our visual world
NAVER D2
 
[231]운영체제 수준에서의 데이터베이스 성능 분석과 최적화
[231]운영체제 수준에서의 데이터베이스 성능 분석과 최적화[231]운영체제 수준에서의 데이터베이스 성능 분석과 최적화
[231]운영체제 수준에서의 데이터베이스 성능 분석과 최적화
NAVER D2
 
[246]reasoning, attention and memory toward differentiable reasoning machines
[246]reasoning, attention and memory   toward differentiable reasoning machines[246]reasoning, attention and memory   toward differentiable reasoning machines
[246]reasoning, attention and memory toward differentiable reasoning machines
NAVER D2
 
[221]똑똑한 인공지능 dj 비서 clova music
[221]똑똑한 인공지능 dj 비서 clova music[221]똑똑한 인공지능 dj 비서 clova music
[221]똑똑한 인공지능 dj 비서 clova music
NAVER D2
 
[223]rye, 샤딩을 지원하는 오픈소스 관계형 dbms
[223]rye, 샤딩을 지원하는 오픈소스 관계형 dbms[223]rye, 샤딩을 지원하는 오픈소스 관계형 dbms
[223]rye, 샤딩을 지원하는 오픈소스 관계형 dbms
NAVER D2
 
[222]neural machine translation (nmt) 동작의 시각화 및 분석 방법
[222]neural machine translation (nmt) 동작의 시각화 및 분석 방법[222]neural machine translation (nmt) 동작의 시각화 및 분석 방법
[222]neural machine translation (nmt) 동작의 시각화 및 분석 방법
NAVER D2
 
[224]nsml 상상하는 모든 것이 이루어지는 클라우드 머신러닝 플랫폼
[224]nsml 상상하는 모든 것이 이루어지는 클라우드 머신러닝 플랫폼[224]nsml 상상하는 모든 것이 이루어지는 클라우드 머신러닝 플랫폼
[224]nsml 상상하는 모든 것이 이루어지는 클라우드 머신러닝 플랫폼
NAVER D2
 
[212]big models without big data using domain specific deep networks in data-...
[212]big models without big data using domain specific deep networks in data-...[212]big models without big data using domain specific deep networks in data-...
[212]big models without big data using domain specific deep networks in data-...
NAVER D2
 
[234]멀티테넌트 하둡 클러스터 운영 경험기
[234]멀티테넌트 하둡 클러스터 운영 경험기[234]멀티테넌트 하둡 클러스터 운영 경험기
[234]멀티테넌트 하둡 클러스터 운영 경험기
NAVER D2
 
[242]open stack neutron dataplane 구현
[242]open stack neutron   dataplane 구현[242]open stack neutron   dataplane 구현
[242]open stack neutron dataplane 구현
NAVER D2
 
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
NAVER D2
 
[213] 의료 ai를 위해 세상에 없는 양질의 data 만드는 도구 제작하기
[213] 의료 ai를 위해 세상에 없는 양질의 data 만드는 도구 제작하기[213] 의료 ai를 위해 세상에 없는 양질의 data 만드는 도구 제작하기
[213] 의료 ai를 위해 세상에 없는 양질의 data 만드는 도구 제작하기
NAVER D2
 
인공지능추천시스템 airs개발기_모델링과시스템
인공지능추천시스템 airs개발기_모델링과시스템인공지능추천시스템 airs개발기_모델링과시스템
인공지능추천시스템 airs개발기_모델링과시스템
NAVER D2
 
[232]mist 고성능 iot 스트림 처리 시스템
[232]mist 고성능 iot 스트림 처리 시스템[232]mist 고성능 iot 스트림 처리 시스템
[232]mist 고성능 iot 스트림 처리 시스템
NAVER D2
 
[225]빅데이터를 위한 분산 딥러닝 플랫폼 만들기
[225]빅데이터를 위한 분산 딥러닝 플랫폼 만들기[225]빅데이터를 위한 분산 딥러닝 플랫폼 만들기
[225]빅데이터를 위한 분산 딥러닝 플랫폼 만들기
NAVER D2
 
[211] HBase 기반 검색 데이터 저장소 (공개용)
[211] HBase 기반 검색 데이터 저장소 (공개용)[211] HBase 기반 검색 데이터 저장소 (공개용)
[211] HBase 기반 검색 데이터 저장소 (공개용)
NAVER D2
 
유연하고 확장성 있는 빅데이터 처리
유연하고 확장성 있는 빅데이터 처리유연하고 확장성 있는 빅데이터 처리
유연하고 확장성 있는 빅데이터 처리
NAVER D2
 
[244]네트워크 모니터링 시스템(nms)을 지탱하는 기술
[244]네트워크 모니터링 시스템(nms)을 지탱하는 기술[244]네트워크 모니터링 시스템(nms)을 지탱하는 기술
[244]네트워크 모니터링 시스템(nms)을 지탱하는 기술
NAVER D2
 
[216]네이버 검색 사용자를 만족시켜라! 의도파악과 의미검색
[216]네이버 검색 사용자를 만족시켜라!   의도파악과 의미검색[216]네이버 검색 사용자를 만족시켜라!   의도파악과 의미검색
[216]네이버 검색 사용자를 만족시켜라! 의도파악과 의미검색
NAVER D2
 

Viewers also liked (20)

[241]large scale search with polysemous codes
[241]large scale search with polysemous codes[241]large scale search with polysemous codes
[241]large scale search with polysemous codes
 
[213]building ai to recreate our visual world
[213]building ai to recreate our visual world[213]building ai to recreate our visual world
[213]building ai to recreate our visual world
 
[231]운영체제 수준에서의 데이터베이스 성능 분석과 최적화
[231]운영체제 수준에서의 데이터베이스 성능 분석과 최적화[231]운영체제 수준에서의 데이터베이스 성능 분석과 최적화
[231]운영체제 수준에서의 데이터베이스 성능 분석과 최적화
 
[246]reasoning, attention and memory toward differentiable reasoning machines
[246]reasoning, attention and memory   toward differentiable reasoning machines[246]reasoning, attention and memory   toward differentiable reasoning machines
[246]reasoning, attention and memory toward differentiable reasoning machines
 
[221]똑똑한 인공지능 dj 비서 clova music
[221]똑똑한 인공지능 dj 비서 clova music[221]똑똑한 인공지능 dj 비서 clova music
[221]똑똑한 인공지능 dj 비서 clova music
 
[223]rye, 샤딩을 지원하는 오픈소스 관계형 dbms
[223]rye, 샤딩을 지원하는 오픈소스 관계형 dbms[223]rye, 샤딩을 지원하는 오픈소스 관계형 dbms
[223]rye, 샤딩을 지원하는 오픈소스 관계형 dbms
 
[222]neural machine translation (nmt) 동작의 시각화 및 분석 방법
[222]neural machine translation (nmt) 동작의 시각화 및 분석 방법[222]neural machine translation (nmt) 동작의 시각화 및 분석 방법
[222]neural machine translation (nmt) 동작의 시각화 및 분석 방법
 
[224]nsml 상상하는 모든 것이 이루어지는 클라우드 머신러닝 플랫폼
[224]nsml 상상하는 모든 것이 이루어지는 클라우드 머신러닝 플랫폼[224]nsml 상상하는 모든 것이 이루어지는 클라우드 머신러닝 플랫폼
[224]nsml 상상하는 모든 것이 이루어지는 클라우드 머신러닝 플랫폼
 
[212]big models without big data using domain specific deep networks in data-...
[212]big models without big data using domain specific deep networks in data-...[212]big models without big data using domain specific deep networks in data-...
[212]big models without big data using domain specific deep networks in data-...
 
[234]멀티테넌트 하둡 클러스터 운영 경험기
[234]멀티테넌트 하둡 클러스터 운영 경험기[234]멀티테넌트 하둡 클러스터 운영 경험기
[234]멀티테넌트 하둡 클러스터 운영 경험기
 
[242]open stack neutron dataplane 구현
[242]open stack neutron   dataplane 구현[242]open stack neutron   dataplane 구현
[242]open stack neutron dataplane 구현
 
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
 
[213] 의료 ai를 위해 세상에 없는 양질의 data 만드는 도구 제작하기
[213] 의료 ai를 위해 세상에 없는 양질의 data 만드는 도구 제작하기[213] 의료 ai를 위해 세상에 없는 양질의 data 만드는 도구 제작하기
[213] 의료 ai를 위해 세상에 없는 양질의 data 만드는 도구 제작하기
 
인공지능추천시스템 airs개발기_모델링과시스템
인공지능추천시스템 airs개발기_모델링과시스템인공지능추천시스템 airs개발기_모델링과시스템
인공지능추천시스템 airs개발기_모델링과시스템
 
[232]mist 고성능 iot 스트림 처리 시스템
[232]mist 고성능 iot 스트림 처리 시스템[232]mist 고성능 iot 스트림 처리 시스템
[232]mist 고성능 iot 스트림 처리 시스템
 
[225]빅데이터를 위한 분산 딥러닝 플랫폼 만들기
[225]빅데이터를 위한 분산 딥러닝 플랫폼 만들기[225]빅데이터를 위한 분산 딥러닝 플랫폼 만들기
[225]빅데이터를 위한 분산 딥러닝 플랫폼 만들기
 
[211] HBase 기반 검색 데이터 저장소 (공개용)
[211] HBase 기반 검색 데이터 저장소 (공개용)[211] HBase 기반 검색 데이터 저장소 (공개용)
[211] HBase 기반 검색 데이터 저장소 (공개용)
 
유연하고 확장성 있는 빅데이터 처리
유연하고 확장성 있는 빅데이터 처리유연하고 확장성 있는 빅데이터 처리
유연하고 확장성 있는 빅데이터 처리
 
[244]네트워크 모니터링 시스템(nms)을 지탱하는 기술
[244]네트워크 모니터링 시스템(nms)을 지탱하는 기술[244]네트워크 모니터링 시스템(nms)을 지탱하는 기술
[244]네트워크 모니터링 시스템(nms)을 지탱하는 기술
 
[216]네이버 검색 사용자를 만족시켜라! 의도파악과 의미검색
[216]네이버 검색 사용자를 만족시켜라!   의도파악과 의미검색[216]네이버 검색 사용자를 만족시켜라!   의도파악과 의미검색
[216]네이버 검색 사용자를 만족시켜라! 의도파악과 의미검색
 

Similar to [215]streetwise machine learning for painless parking

Dynamic Pricing in Ride-Hailing Platforms
Dynamic Pricing in Ride-Hailing PlatformsDynamic Pricing in Ride-Hailing Platforms
Dynamic Pricing in Ride-Hailing Platforms
Hamed Shams
 
Applications Of Math In Real Life And Business
Applications Of Math In Real Life And BusinessApplications Of Math In Real Life And Business
Applications Of Math In Real Life And Business
Muhammad Ahmad Badar
 
presentation data fusion methods ex.pptx
presentation data fusion methods ex.pptxpresentation data fusion methods ex.pptx
presentation data fusion methods ex.pptx
Julius346776
 
PRACTICAL APPLICATION OF MATHEMATICS- BASICS
PRACTICAL APPLICATION OF MATHEMATICS- BASICSPRACTICAL APPLICATION OF MATHEMATICS- BASICS
PRACTICAL APPLICATION OF MATHEMATICS- BASICS
Shameem P Yousef
 
Machine Learning statistical model using Transportation data
Machine Learning statistical model using Transportation dataMachine Learning statistical model using Transportation data
Machine Learning statistical model using Transportation data
jagan477830
 
Mb0048 operations research
Mb0048   operations researchMb0048   operations research
Mb0048 operations research
smumbahelp
 
HunchLab 2.0 Predictive Missions: Under the Hood
HunchLab 2.0 Predictive Missions: Under the HoodHunchLab 2.0 Predictive Missions: Under the Hood
HunchLab 2.0 Predictive Missions: Under the HoodAzavea
 
Machine learning and linear regression programming
Machine learning and linear regression programmingMachine learning and linear regression programming
Machine learning and linear regression programming
Soumya Mukherjee
 
2014-mo444-final-project
2014-mo444-final-project2014-mo444-final-project
2014-mo444-final-projectPaulo Faria
 
Ilab Metis: we optimize power systems and we are not afraid of direct policy ...
Ilab Metis: we optimize power systems and we are not afraid of direct policy ...Ilab Metis: we optimize power systems and we are not afraid of direct policy ...
Ilab Metis: we optimize power systems and we are not afraid of direct policy ...
Olivier Teytaud
 
Analysis of waiting line processes - U3.pptx
Analysis of waiting line processes - U3.pptxAnalysis of waiting line processes - U3.pptx
Analysis of waiting line processes - U3.pptx
MariaBurgos55
 
Particle Swarm Optimization to Solve Multiple Traveling Salesman Problem
Particle Swarm Optimization to Solve Multiple Traveling Salesman ProblemParticle Swarm Optimization to Solve Multiple Traveling Salesman Problem
Particle Swarm Optimization to Solve Multiple Traveling Salesman Problem
IRJET Journal
 
Real Estate Investment Advising Using Machine Learning
Real Estate Investment Advising Using Machine LearningReal Estate Investment Advising Using Machine Learning
Real Estate Investment Advising Using Machine Learning
IRJET Journal
 
Comp prese (1)
Comp prese (1)Comp prese (1)
Comp prese (1)
Mohmmad Khasawneh
 
IEOR 265 Final Paper_Minchao Lin
IEOR 265 Final Paper_Minchao LinIEOR 265 Final Paper_Minchao Lin
IEOR 265 Final Paper_Minchao LinMinchao Lin
 
Paper review: Learned Optimizers that Scale and Generalize.
Paper review: Learned Optimizers that Scale and Generalize.Paper review: Learned Optimizers that Scale and Generalize.
Paper review: Learned Optimizers that Scale and Generalize.
Wuhyun Rico Shin
 
11 2016 jit-dumping_ss360
11 2016 jit-dumping_ss36011 2016 jit-dumping_ss360
11 2016 jit-dumping_ss360
Yvonne C. Salazar
 
Long-Term Robust Tracking Whith on Failure Recovery
Long-Term Robust Tracking Whith on Failure RecoveryLong-Term Robust Tracking Whith on Failure Recovery
Long-Term Robust Tracking Whith on Failure Recovery
TELKOMNIKA JOURNAL
 

Similar to [215]streetwise machine learning for painless parking (20)

Dynamic Pricing in Ride-Hailing Platforms
Dynamic Pricing in Ride-Hailing PlatformsDynamic Pricing in Ride-Hailing Platforms
Dynamic Pricing in Ride-Hailing Platforms
 
Applications Of Math In Real Life And Business
Applications Of Math In Real Life And BusinessApplications Of Math In Real Life And Business
Applications Of Math In Real Life And Business
 
presentation data fusion methods ex.pptx
presentation data fusion methods ex.pptxpresentation data fusion methods ex.pptx
presentation data fusion methods ex.pptx
 
PRACTICAL APPLICATION OF MATHEMATICS- BASICS
PRACTICAL APPLICATION OF MATHEMATICS- BASICSPRACTICAL APPLICATION OF MATHEMATICS- BASICS
PRACTICAL APPLICATION OF MATHEMATICS- BASICS
 
Where Next
Where NextWhere Next
Where Next
 
Machine Learning statistical model using Transportation data
Machine Learning statistical model using Transportation dataMachine Learning statistical model using Transportation data
Machine Learning statistical model using Transportation data
 
Mb0048 operations research
Mb0048   operations researchMb0048   operations research
Mb0048 operations research
 
HunchLab 2.0 Predictive Missions: Under the Hood
HunchLab 2.0 Predictive Missions: Under the HoodHunchLab 2.0 Predictive Missions: Under the Hood
HunchLab 2.0 Predictive Missions: Under the Hood
 
Machine learning and linear regression programming
Machine learning and linear regression programmingMachine learning and linear regression programming
Machine learning and linear regression programming
 
2014-mo444-final-project
2014-mo444-final-project2014-mo444-final-project
2014-mo444-final-project
 
Ilab Metis: we optimize power systems and we are not afraid of direct policy ...
Ilab Metis: we optimize power systems and we are not afraid of direct policy ...Ilab Metis: we optimize power systems and we are not afraid of direct policy ...
Ilab Metis: we optimize power systems and we are not afraid of direct policy ...
 
Analysis of waiting line processes - U3.pptx
Analysis of waiting line processes - U3.pptxAnalysis of waiting line processes - U3.pptx
Analysis of waiting line processes - U3.pptx
 
Particle Swarm Optimization to Solve Multiple Traveling Salesman Problem
Particle Swarm Optimization to Solve Multiple Traveling Salesman ProblemParticle Swarm Optimization to Solve Multiple Traveling Salesman Problem
Particle Swarm Optimization to Solve Multiple Traveling Salesman Problem
 
Real Estate Investment Advising Using Machine Learning
Real Estate Investment Advising Using Machine LearningReal Estate Investment Advising Using Machine Learning
Real Estate Investment Advising Using Machine Learning
 
Comp prese (1)
Comp prese (1)Comp prese (1)
Comp prese (1)
 
PCA.pptx
PCA.pptxPCA.pptx
PCA.pptx
 
IEOR 265 Final Paper_Minchao Lin
IEOR 265 Final Paper_Minchao LinIEOR 265 Final Paper_Minchao Lin
IEOR 265 Final Paper_Minchao Lin
 
Paper review: Learned Optimizers that Scale and Generalize.
Paper review: Learned Optimizers that Scale and Generalize.Paper review: Learned Optimizers that Scale and Generalize.
Paper review: Learned Optimizers that Scale and Generalize.
 
11 2016 jit-dumping_ss360
11 2016 jit-dumping_ss36011 2016 jit-dumping_ss360
11 2016 jit-dumping_ss360
 
Long-Term Robust Tracking Whith on Failure Recovery
Long-Term Robust Tracking Whith on Failure RecoveryLong-Term Robust Tracking Whith on Failure Recovery
Long-Term Robust Tracking Whith on Failure Recovery
 

More from NAVER D2

[211] 인공지능이 인공지능 챗봇을 만든다
[211] 인공지능이 인공지능 챗봇을 만든다[211] 인공지능이 인공지능 챗봇을 만든다
[211] 인공지능이 인공지능 챗봇을 만든다
NAVER D2
 
[233] 대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing: Maglev Hashing Scheduler i...
[233] 대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing: Maglev Hashing Scheduler i...[233] 대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing: Maglev Hashing Scheduler i...
[233] 대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing: Maglev Hashing Scheduler i...
NAVER D2
 
[215] Druid로 쉽고 빠르게 데이터 분석하기
[215] Druid로 쉽고 빠르게 데이터 분석하기[215] Druid로 쉽고 빠르게 데이터 분석하기
[215] Druid로 쉽고 빠르게 데이터 분석하기
NAVER D2
 
[245]Papago Internals: 모델분석과 응용기술 개발
[245]Papago Internals: 모델분석과 응용기술 개발[245]Papago Internals: 모델분석과 응용기술 개발
[245]Papago Internals: 모델분석과 응용기술 개발
NAVER D2
 
[236] 스트림 저장소 최적화 이야기: 아파치 드루이드로부터 얻은 교훈
[236] 스트림 저장소 최적화 이야기: 아파치 드루이드로부터 얻은 교훈[236] 스트림 저장소 최적화 이야기: 아파치 드루이드로부터 얻은 교훈
[236] 스트림 저장소 최적화 이야기: 아파치 드루이드로부터 얻은 교훈
NAVER D2
 
[235]Wikipedia-scale Q&A
[235]Wikipedia-scale Q&A[235]Wikipedia-scale Q&A
[235]Wikipedia-scale Q&A
NAVER D2
 
[244]로봇이 현실 세계에 대해 학습하도록 만들기
[244]로봇이 현실 세계에 대해 학습하도록 만들기[244]로봇이 현실 세계에 대해 학습하도록 만들기
[244]로봇이 현실 세계에 대해 학습하도록 만들기
NAVER D2
 
[243] Deep Learning to help student’s Deep Learning
[243] Deep Learning to help student’s Deep Learning[243] Deep Learning to help student’s Deep Learning
[243] Deep Learning to help student’s Deep Learning
NAVER D2
 
[234]Fast & Accurate Data Annotation Pipeline for AI applications
[234]Fast & Accurate Data Annotation Pipeline for AI applications[234]Fast & Accurate Data Annotation Pipeline for AI applications
[234]Fast & Accurate Data Annotation Pipeline for AI applications
NAVER D2
 
Old version: [233]대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing
Old version: [233]대형 컨테이너 클러스터에서의 고가용성 Network Load BalancingOld version: [233]대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing
Old version: [233]대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing
NAVER D2
 
[226]NAVER 광고 deep click prediction: 모델링부터 서빙까지
[226]NAVER 광고 deep click prediction: 모델링부터 서빙까지[226]NAVER 광고 deep click prediction: 모델링부터 서빙까지
[226]NAVER 광고 deep click prediction: 모델링부터 서빙까지
NAVER D2
 
[225]NSML: 머신러닝 플랫폼 서비스하기 & 모델 튜닝 자동화하기
[225]NSML: 머신러닝 플랫폼 서비스하기 & 모델 튜닝 자동화하기[225]NSML: 머신러닝 플랫폼 서비스하기 & 모델 튜닝 자동화하기
[225]NSML: 머신러닝 플랫폼 서비스하기 & 모델 튜닝 자동화하기
NAVER D2
 
[224]네이버 검색과 개인화
[224]네이버 검색과 개인화[224]네이버 검색과 개인화
[224]네이버 검색과 개인화
NAVER D2
 
[216]Search Reliability Engineering (부제: 지진에도 흔들리지 않는 네이버 검색시스템)
[216]Search Reliability Engineering (부제: 지진에도 흔들리지 않는 네이버 검색시스템)[216]Search Reliability Engineering (부제: 지진에도 흔들리지 않는 네이버 검색시스템)
[216]Search Reliability Engineering (부제: 지진에도 흔들리지 않는 네이버 검색시스템)
NAVER D2
 
[214] Ai Serving Platform: 하루 수 억 건의 인퍼런스를 처리하기 위한 고군분투기
[214] Ai Serving Platform: 하루 수 억 건의 인퍼런스를 처리하기 위한 고군분투기[214] Ai Serving Platform: 하루 수 억 건의 인퍼런스를 처리하기 위한 고군분투기
[214] Ai Serving Platform: 하루 수 억 건의 인퍼런스를 처리하기 위한 고군분투기
NAVER D2
 
[213] Fashion Visual Search
[213] Fashion Visual Search[213] Fashion Visual Search
[213] Fashion Visual Search
NAVER D2
 
[232] TensorRT를 활용한 딥러닝 Inference 최적화
[232] TensorRT를 활용한 딥러닝 Inference 최적화[232] TensorRT를 활용한 딥러닝 Inference 최적화
[232] TensorRT를 활용한 딥러닝 Inference 최적화
NAVER D2
 
[242]컴퓨터 비전을 이용한 실내 지도 자동 업데이트 방법: 딥러닝을 통한 POI 변화 탐지
[242]컴퓨터 비전을 이용한 실내 지도 자동 업데이트 방법: 딥러닝을 통한 POI 변화 탐지[242]컴퓨터 비전을 이용한 실내 지도 자동 업데이트 방법: 딥러닝을 통한 POI 변화 탐지
[242]컴퓨터 비전을 이용한 실내 지도 자동 업데이트 방법: 딥러닝을 통한 POI 변화 탐지
NAVER D2
 
[212]C3, 데이터 처리에서 서빙까지 가능한 하둡 클러스터
[212]C3, 데이터 처리에서 서빙까지 가능한 하둡 클러스터[212]C3, 데이터 처리에서 서빙까지 가능한 하둡 클러스터
[212]C3, 데이터 처리에서 서빙까지 가능한 하둡 클러스터
NAVER D2
 
[223]기계독해 QA: 검색인가, NLP인가?
[223]기계독해 QA: 검색인가, NLP인가?[223]기계독해 QA: 검색인가, NLP인가?
[223]기계독해 QA: 검색인가, NLP인가?
NAVER D2
 

More from NAVER D2 (20)

[211] 인공지능이 인공지능 챗봇을 만든다
[211] 인공지능이 인공지능 챗봇을 만든다[211] 인공지능이 인공지능 챗봇을 만든다
[211] 인공지능이 인공지능 챗봇을 만든다
 
[233] 대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing: Maglev Hashing Scheduler i...
[233] 대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing: Maglev Hashing Scheduler i...[233] 대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing: Maglev Hashing Scheduler i...
[233] 대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing: Maglev Hashing Scheduler i...
 
[215] Druid로 쉽고 빠르게 데이터 분석하기
[215] Druid로 쉽고 빠르게 데이터 분석하기[215] Druid로 쉽고 빠르게 데이터 분석하기
[215] Druid로 쉽고 빠르게 데이터 분석하기
 
[245]Papago Internals: 모델분석과 응용기술 개발
[245]Papago Internals: 모델분석과 응용기술 개발[245]Papago Internals: 모델분석과 응용기술 개발
[245]Papago Internals: 모델분석과 응용기술 개발
 
[236] 스트림 저장소 최적화 이야기: 아파치 드루이드로부터 얻은 교훈
[236] 스트림 저장소 최적화 이야기: 아파치 드루이드로부터 얻은 교훈[236] 스트림 저장소 최적화 이야기: 아파치 드루이드로부터 얻은 교훈
[236] 스트림 저장소 최적화 이야기: 아파치 드루이드로부터 얻은 교훈
 
[235]Wikipedia-scale Q&A
[235]Wikipedia-scale Q&A[235]Wikipedia-scale Q&A
[235]Wikipedia-scale Q&A
 
[244]로봇이 현실 세계에 대해 학습하도록 만들기
[244]로봇이 현실 세계에 대해 학습하도록 만들기[244]로봇이 현실 세계에 대해 학습하도록 만들기
[244]로봇이 현실 세계에 대해 학습하도록 만들기
 
[243] Deep Learning to help student’s Deep Learning
[243] Deep Learning to help student’s Deep Learning[243] Deep Learning to help student’s Deep Learning
[243] Deep Learning to help student’s Deep Learning
 
[234]Fast & Accurate Data Annotation Pipeline for AI applications
[234]Fast & Accurate Data Annotation Pipeline for AI applications[234]Fast & Accurate Data Annotation Pipeline for AI applications
[234]Fast & Accurate Data Annotation Pipeline for AI applications
 
Old version: [233]대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing
Old version: [233]대형 컨테이너 클러스터에서의 고가용성 Network Load BalancingOld version: [233]대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing
Old version: [233]대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing
 
[226]NAVER 광고 deep click prediction: 모델링부터 서빙까지
[226]NAVER 광고 deep click prediction: 모델링부터 서빙까지[226]NAVER 광고 deep click prediction: 모델링부터 서빙까지
[226]NAVER 광고 deep click prediction: 모델링부터 서빙까지
 
[225]NSML: 머신러닝 플랫폼 서비스하기 & 모델 튜닝 자동화하기
[225]NSML: 머신러닝 플랫폼 서비스하기 & 모델 튜닝 자동화하기[225]NSML: 머신러닝 플랫폼 서비스하기 & 모델 튜닝 자동화하기
[225]NSML: 머신러닝 플랫폼 서비스하기 & 모델 튜닝 자동화하기
 
[224]네이버 검색과 개인화
[224]네이버 검색과 개인화[224]네이버 검색과 개인화
[224]네이버 검색과 개인화
 
[216]Search Reliability Engineering (부제: 지진에도 흔들리지 않는 네이버 검색시스템)
[216]Search Reliability Engineering (부제: 지진에도 흔들리지 않는 네이버 검색시스템)[216]Search Reliability Engineering (부제: 지진에도 흔들리지 않는 네이버 검색시스템)
[216]Search Reliability Engineering (부제: 지진에도 흔들리지 않는 네이버 검색시스템)
 
[214] Ai Serving Platform: 하루 수 억 건의 인퍼런스를 처리하기 위한 고군분투기
[214] Ai Serving Platform: 하루 수 억 건의 인퍼런스를 처리하기 위한 고군분투기[214] Ai Serving Platform: 하루 수 억 건의 인퍼런스를 처리하기 위한 고군분투기
[214] Ai Serving Platform: 하루 수 억 건의 인퍼런스를 처리하기 위한 고군분투기
 
[213] Fashion Visual Search
[213] Fashion Visual Search[213] Fashion Visual Search
[213] Fashion Visual Search
 
[232] TensorRT를 활용한 딥러닝 Inference 최적화
[232] TensorRT를 활용한 딥러닝 Inference 최적화[232] TensorRT를 활용한 딥러닝 Inference 최적화
[232] TensorRT를 활용한 딥러닝 Inference 최적화
 
[242]컴퓨터 비전을 이용한 실내 지도 자동 업데이트 방법: 딥러닝을 통한 POI 변화 탐지
[242]컴퓨터 비전을 이용한 실내 지도 자동 업데이트 방법: 딥러닝을 통한 POI 변화 탐지[242]컴퓨터 비전을 이용한 실내 지도 자동 업데이트 방법: 딥러닝을 통한 POI 변화 탐지
[242]컴퓨터 비전을 이용한 실내 지도 자동 업데이트 방법: 딥러닝을 통한 POI 변화 탐지
 
[212]C3, 데이터 처리에서 서빙까지 가능한 하둡 클러스터
[212]C3, 데이터 처리에서 서빙까지 가능한 하둡 클러스터[212]C3, 데이터 처리에서 서빙까지 가능한 하둡 클러스터
[212]C3, 데이터 처리에서 서빙까지 가능한 하둡 클러스터
 
[223]기계독해 QA: 검색인가, NLP인가?
[223]기계독해 QA: 검색인가, NLP인가?[223]기계독해 QA: 검색인가, NLP인가?
[223]기계독해 QA: 검색인가, NLP인가?
 

Recently uploaded

Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
DianaGray10
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
Product School
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
Product School
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User Group
CatarinaPereira64715
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi
Fwdays
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Tobias Schneck
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
Abida Shariff
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
Paul Groth
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
Frank van Harmelen
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
Product School
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Product School
 

Recently uploaded (20)

Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User Group
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
 

[215]streetwise machine learning for painless parking

  • 1. Streetwise Machine Learning for Painless Parking Christopher R. Dance
  • 2. Plan 1. Parking data context 2. Pricing 3. Sampling
  • 4. 1. Parking Data What? mobile cameras, cell phonespolicies, mapsin-street sensors traffic flow special events, …satellites (pollution) surveys payments, violations
  • 5. 1. Parking Data Why? Use cases 1. set parking policy: prices, demarcation, … 2. guide enforcement officers to offenders 3. guide drivers to the best vacancies Value 1. less time wasted finding a space 2. less pollution, better health 3. access to local businesses 4. fair-and-transparent Challenge maximise the utility (value minus cost) of the data
  • 6. 1. Parking Data Who? Many cities have deployed smart parking systems since 2010 San Francisco, London, Moscow, … Our contributions Since 2012, we have deployed 6 new technologies in 3 major cities Los Angeles. Basic pricing method, time-of-week subdivision, real-time pricing as rate, optimal learning while selling, surveys, effectiveness evaluation, non-payment evaluation (and not deployed: real-time parking guidance, real-time pricing as integral) Washington DC. Spatiotemporal sampling: sensor allocation and reconstruction, spatial queueing for demarcation decisions Berkeley. Fusion of temporal sampling with payment data Awards for this work included ITS Innovation, IPI Innovation and MIT Top-50
  • 8. Zoeter et al , New Algorithms for Parking Demand Management. Proc. 20th ACM KDD, 2014 Glasnapp et al, Understanding Dynamic Pricing for Parking in Los Angeles. Intl. Conf. HCI in Business, 2014 2. Pricing Context. Demand-Based Pricing
  • 9. 2. Pricing Problem Learn on-street parking prices to make the city happier ⇒ maximize the rate at which people get value from the system (not revenue) Challenges 1. Model or forecast for value when driver behavior varies in 5 dimensions frequency, location, arrival, duration, legality-fraction 2. Ensure simplicity so drivers remember and city official can explain in the face of huge variations in demand in space and time 3. How big should price increments be? too large ⇒ prices might oscillate from month-to-month too small ⇒ system may have no useful effect
  • 10. 2. Pricing Model for Value Goal. Choose appropriate reward function If more people are parked, then • more people get value • but the distance to a space increases For a geometric distribution of vacancies distance to a space = 𝑓 1−𝑓 where the occupancy fraction is 𝑓 But this is singular as 𝑓 → 1! occupancy fraction mean spaces to first vacancy - geometric distribution
  • 11. 2. Pricing Distance to a Space The singularity is unrealistic as occupancy fractions vary spatially spatial autocorrelation of occupancy fraction (LA 2012 data) mean spaces to first vacancy - geometric distribution - real data occupancy fraction
  • 12. 2. Pricing Simple Valuation Model occupancy fraction Gradient Ascent Move up the gradient of the total valuation w.r.t. price 𝒑, so new-price – old-price ∼ 𝝏 𝝏𝒑 ‫׬‬𝓡 valuation−rate 𝒑, 𝒕, 𝒙 𝒅𝒙 𝒅𝒕 ⇒ simple for machine-learning scientists, but NOT for citizens and officials... valuation rate (per space, per unit time) = constant per person parked - k × distance travelled per arrival
  • 13. 2. Pricing Simple Valuation Model occupancy fraction ⇒ simple for machine-learning scientists, but NOT for citizens and officials… valuation rate (per space, per unit time) = constant per person parked - k × distance travelled per arrival Towards a simpler rule Maximizing the black curve is nearly the same as maximizing the red curve, whose gradients are -1, 0 or 1 approximation Gradient Ascent Move up the gradient of the total valuation w.r.t. price 𝒑, so new-price – old-price ∼ 𝝏 𝝏𝒑 ‫׬‬𝓡 valuation−rate 𝒑, 𝒕, 𝒙 𝒅𝒙 𝒅𝒕
  • 14. 2. Pricing Voting Rule Voting Rule If 𝑯 − 𝑳 > 0.3 then increase the price If 𝑳 − 𝑯 > 0.3 then decrease the price Prices are on a ladder $0.5, $1, $1.50, $2, $3, …, $7 per hour Definition The high vote, 𝑯, is the fraction of time that the system is over 90% occupied The low vote, 𝑳, is the fraction of time that the system is under 70% occupied
  • 15. 2. Pricing (A Tale of Two Cities) Comparison Average Occupancy Rule (used in San Francisco) If average occupancy fraction > 𝟎. 𝟖 then increase the price by $0.25 If average occupancy fraction < 𝟎. 𝟔 then decrease the price by $0.25 average occupancy fraction 0.67 0.67 average occupancy rule price same price same voting rule price down price up mean distance to vacancy 2 spaces 11 spaces occupancy fraction Scenario A Scenario B
  • 16. 2. Pricing - How did prices ($/HR) change? Area is proportional to the sum over spaces of the number of hours at the given price Before (1st June 2012) After (1st January 2013) $5 $4 $3 $2 $150 $1 $050 $4 $3 $2 $1 50% of prices decreased yet revenue increased by 12%
  • 17. 2. Pricing Does it work? Price increase from $4/hour to $5/hour No vacancy = full (red) More availability (yellow and green) Occupancy time series for 701 South Olive Street, one row = one weekday (Mon-Fri not Sat-Sun) Underused (blue) … but is this • the impact of the price change • a change in sensor signal-processing • a lucky coincidence • something else?
  • 18. March-June 2012 June-December 2012 2. Pricing Does it work? # congested spaces (≥ 18 of closest neighbours occupied) 11AM Noon 1PM 2PM 3PM 4PM 300 400 500 600 700 800 900 1000 1100 1200 1300 11AM Noon 1PM 2PM 3PM 4PM 2800 3000 3200 3400 3600 3800 4000 4200 4400 4600 4800 # under-used spaces (≤ 14 of closest neighbours occupied) 10% reduction 5% reduction
  • 19. Handicapped placards • 80% of parking in highly-congested areas now goes for free to handicapped placard users • Maybe, many such drivers use placards illegally • Law-changing takes time, but is ongoing Minimum price • The minimum acceptable price ($0.5 per hour) was already reached in under-used areas • But occupancy there has continued to increase substantially • It’s hard to distinguish between economic improvement and long-term price-change latency Political acceptance Unlike SFPark, LA ExpressPark receives positive press coverage and continues to expand today Clinchant et al, Using Analytics to Understand On-Street Parking. Proc. 22nd World Congress on ITS, 2015 2. Pricing Does it work? Results for 2013-16
  • 21. 3. Sampling Motivation Solutions 1. Spatial sampling: don’t observe all stalls 2. Temporal sampling: don’t observe all the time Deployed in Washington DC and Berkeley Problem LA’s sensors are too expensive. Can we combine sensing methods to ensure high- quality data while saving 90% of the costs? Dance, Lean Smart Parking. The Parking Professional, vol. 30, no. 6, 2014
  • 22. 3. Sampling Problem P1 Informally Given • a normally-distributed discrete-time time-series • noisy measurements that come at a cost Question When should you measure so as to minimise the cost of prediction errors plus measurement costs? black = true time-series (unobserved) red = forecast standard-deviation blue = costly measurements Formally Time-series 𝑿 𝒕+𝟏 = 𝑨𝑿 𝒕 + 𝑵(𝟎, 𝑸) Actions 𝑎 𝑡 = 1 for good measurement, cost 𝑐 𝑎 𝑡 = 0 for poor measurement, no cost Measurements 𝒀 𝒕 = 𝑩𝑿 𝒕 + 𝑵 𝟎, 𝑹(𝒂 𝒕) History 𝐻𝑡 = (𝑎1, 𝑎2, … , 𝑎 𝑡−1, 𝒀 𝟏, 𝒀 𝟐, … , 𝒀𝒕−𝟏) Policy 𝑎 𝑡 = 𝜋(𝐻𝑡) Forecasts ෡𝑿 𝒕 = 𝐄 𝑿 𝒕 𝐻𝑡] given by the Kalman filter Objective min 𝜋 𝐄 σ 𝑡=1 ∞ 𝛾 𝑡 ෡𝑿 𝒕 − 𝑿 𝒕 2 + 𝑐 𝑎 𝑡 time
  • 23. 3. Sampling Problem P1: Examples Parking time-series occupancy of a block face measurements from mobile cameras and payment data Military time-series position of a submarine measurements by sonar Telecommunications time-series position of a handset measurements with 5G antenna
  • 24. 3. Sampling Problem P1: Related Work P1 addresses the basic machine learning trade-off between • the cost of data acquisition • the cost of errors due to a lack of data in a particularly simple way If we solve P1, then we also solve • “the LQG control problem with costly measurements”(Meier et al, 1967) The continuous-time version of this problem was solved only recently (Le Ny et al, 2011) Niño-Mora and Villar (2009) conjectured that an optimal policy for P1 is a threshold policy • i.e. measure if and only if the posterior variance exceeds a threshold. Meier et al, Optimal control of measurement subsystems. IEEE TAC, 1967 Le Ny et al, Scheduling continuous-time Kalman filters. IEEE TAC, 2011 Niño-Mora and Villar, Multi-target tracking via restless bandit marginal productivity indices. IEEE CDC, 2009
  • 25. 3. Sampling Attention Mechanism Problem Street 1 Street 2 Street 3 observation times Given • 𝑛 time-series to track, as in P1 • with 𝑚 sensors, where 𝑚 < 𝑛 Question Which time-series should you measure at each time, so as to minimise the total prediction error? Discussion • This problem has state space ℝ 𝑛 and 𝑛 𝑚 actions! • Nevertheless, Whittle (1988) proposed a computationally-efficient policy for this problem for large 𝑚, 𝑛 • But to compute that policy, we must first solve P1 Example • 4 cameras observing 800 streets in Washington DC • This was our original motivation for this work Whittle, Restless bandits: activity allocation in a changing world. J. App. Prob., 1988
  • 26. 3. Sampling Attention Mechanism Problem Claim. Assuming P1 is solved, Whittle’s policy does much better than other heuristics Example. 10 time-series, 1 sensor, weights on predictive variance 𝑤1 = 40, 𝑤2:10 = 1 time-series time, 𝑡 colour = weighted prediction error Myopic policy Observes the time-series with the largest weighted predictive variance (often used in radar tracking) Round-robin policy Observes time-series 1, 2, …, 10, 1, 2, …, 10, … Whittle’s policy
  • 27. 3. Sampling Solution to P1 Dance and Silander, When are Kalman-Filter Restless Bandits Indexable? NIPS, 2015 Dance and Silander, Optimal Policies for Observing Time Series, in review, JMLR, 2017 (see arXiv) Theorem (Dance and Silander, 2017) 1. A threshold policy is optimal for Problem P1 2. This result holds for many cost functions minimum predictive variance, minimum predictive entropy, maximum predictive precision, … 3. There is a simple polynomial-time algorithm for approximating the threshold
  • 28. 3. Sampling Key to the proof Examine the behaviour of the system under a threshold policy • The state 𝑥𝑡 is given by the predictive variance • Its dynamics are given by the Kalman filter variance updates, which are nonlinear 𝜙0 - no measurement (below threshold) 𝜙1 - measurement made (above threshold) • So, for threshold 𝑧 we have 𝑥𝑡+1 = 𝑓 𝑥𝑡; 𝑧 ≔ ቊ 𝜙0(𝑥𝑡), 𝑥𝑡 < 𝑧 𝜙1(𝑥𝑡), 𝑥𝑡 ≥ 𝑧 action 0 action 1 threshold
  • 29. 3. Sampling Insights: Maps-with-Gaps The behaviour of iterated function systems 𝑥𝑡+1 = 𝑓(𝑥𝑡) has been extensively studied when 𝑓 is smooth But our 𝑓(⋅; 𝑧) is discontinuous Such maps-with-gaps are also important as models of: • switching in electrical circuits • neural spiking behaviour • gene regulatory networks, …
  • 30. 3. Sampling Insights: Words How does the action sequence generated by our map change • as we vary the threshold 𝑧 • from initial state 𝑥1 = 𝑧? The action sequence is an infinite word on the alphabet {0,1} Question What types of word does our map generate? time,𝑡 threshold, 𝑧 black = action 0 white = action 1
  • 31. 3. Sampling Answer: Mechanical Words Definition A mechanical word is an infinite binary string whose 𝑛th letter is 𝑤 𝑛 = 𝑎(𝑛 + 1) − 𝑎𝑛 for some 𝑎 in [0,1]. Examples 𝑎 = 1/2 ⇒ the word 01 01 01 01… 𝑎 = 3/7 ⇒ the word 00100101 00100101 00100101… Mechanical words correspond to the slopes of digital straight lines Relation to the literature • Kozyakin (2003) found general conditions under which nonlinear maps-with-gaps generate mechanical words • However, the relationship between the choice of threshold and the word generated was only discovered for linear maps-with-gaps by Rajpathak et al (2012) • Our work extends this threshold-to-word relationship to nonlinear maps 0 0 0 0 0 1 1 1 Kozyakin, Sturmian sequences generated by order-preserving circle maps. Inst. Information Trans., RAS, 2003 Rajpathak et al, Analysis of stable periodic orbits in the one-dimensional linear discontinuous map. Chaos, 2012
  • 32. 3. Sampling Open Questions • What happens if there are more than 2 types of measurements? • What can be said in the multivariate Gaussian case? • What about non-Gaussian time-series?
  • 34. Outlook 1. Widespread adoption of demand-management technologies makes sense 2. Counting cars with computer vision seems most cost-effective ⇒ room for improvement in accuracy of on-street car counts 3. Forecasting non-demarcated parking remains challenging 4. Parking policy and guidance for autonomous vehicles ⇒ enable more effective mechanisms: routing policies, reservations, options, lotteries, … ⇒ while making life simpler for citizens
  • 35. Q & A