In this presentation, Calvin demonstrates how him and his colleagues used deep neural networks to estimate the solutions for specific travelling salesman problems and to enable the better steering of operations at Zalando's fashion warehouses.
It is the adder used to eliminate the wastage of time occur at each stage of parallel binary adder.In this , by using only carry input signal , we can calculate the the carry output without going to calculate carry at each stage.it is commonly used only for 4 bit addition because further calculation will be more complex.
This talk aims to give overview of memory management and Garbage Collection and a new look to the typical process of Garbage Collection.
Speaker:
Dr. Rifat Shahriyar
Assistant Professor
Department of Computer Science and Engineering
Bangladesh University of Engineering and Technology
It is the adder used to eliminate the wastage of time occur at each stage of parallel binary adder.In this , by using only carry input signal , we can calculate the the carry output without going to calculate carry at each stage.it is commonly used only for 4 bit addition because further calculation will be more complex.
This talk aims to give overview of memory management and Garbage Collection and a new look to the typical process of Garbage Collection.
Speaker:
Dr. Rifat Shahriyar
Assistant Professor
Department of Computer Science and Engineering
Bangladesh University of Engineering and Technology
128-Bit Area Efficient Reconfigurable Carry Select Adder ijcisjournal
Adders are one of the most critical arithmetic circuits in a system and their throughput affects the overall
performance of the system. Carry Select Adder (CSLA) is one of the fastest adders used in many dataprocessing
processors to perform fast arithmetic functions. From the structure of the CSLA, it is clear that
there is scope for reducing the area and power consumption in the CSLA. In this paper, we proposed an
area-efficient carry select adder by sharing the common Boolean logic term. After logic optimization and
sharing partial circuit, we only need one XOR gate and one inverter gate for sum generation. Through the
multiplexer, we can select the final-sum only and for carry selection we need only one AND gate and one
OR gate. Based on this modification 16-, 32-, 64-, and 128-bit CSLA architecture have been developed and
compared with the conventional CSLA architecture. The proposed design greatly reduces the area
compared to other CSLAs. From this improvement, the gate count of a 128-bit carry select adder can be
reduced from 3320 to 1664. The proposed structure is implemented in Artix-7 FPGA. Compared with the
proposed design, the conventional CSLA has 65.80% less area.
Tutorial: The Role of Event-Time Analysis Order in Data StreamingVincenzo Gulisano
Slides for our tutorial, titled “The Role of Event-Time Analysis Order in Data Streaming”, presented at the 14th ACM International Conference on Distributed and Event-Based Systems (DEBS) conference. We have recorded the tutorial, and you can find the videos at the following links:
Part 1: https://youtu.be/SW_WS6ULsdY
Part 2: https://youtu.be/bq3ECNvPwOU
You can find this slides, as well as the code examples, at https://github.com/vincenzo-gulisano/debs2020_tutorial_event_time and at SlideS
The project focuses on how Congestion Control and Queue Management techniques have evolved in the course of time and being modified to minimize packet loss and stabilize Queue length
Opensample: A Low-latency, Sampling-based Measurement Platform for Software D...Junho Suh
In this paper we propose, implement and evaluate OpenSample: a low-latency, sampling-based network measure- ment platform targeted at building faster control loops for software-defined networks. OpenSample leverages sFlow packet sampling to provide near–real-time measurements of both net- work load and individual flows. While OpenSample is useful in any context, it is particularly useful in an SDN environment where a network controller can quickly take action based on the data it provides. Using sampling for network monitoring allows OpenSample to have a 100 millisecond control loop rather than the 1–5 second control loop of prior polling-based approaches. We implement OpenSample in the Floodlight OpenFlow controller and evaluate it both in simulation and on a testbed comprised of commodity switches. When used to inform traffic engineering, OpenSample provides up to a 150% throughput improvement over both static equal-cost multi-path routing and a polling-based solution with a one second control loop.
Modified Headfirst Sliding Routing: A Time-Based Routing Scheme for Bus-Nochy...IJERA Editor
Several interesting topologies emerge by incorporating the third dimension in networks-on-chip (NoC). The Network-on-Chip (NoC) is Network-version of System on-Chip (SoC) means that on-chip communication is done through packet based networks. In NOC topology, routing algorithm and switching are main terminology .The routing algorithm is one of the key factor in NOC architecture. The routing algorithm, which defines as the path taken by a packet between the source and the destination. A good routing algorithm is necessary to improve the network performance. . Here we are proposing a new architecture to improve the throughput and latency of the network. In the proposed approach we are using a fixed path for the packet to transmit from source to destination
Crash course on data streaming (with examples using Apache Flink)Vincenzo Gulisano
These are the slides I used for a crash course (4 hours) on data streaming. It contains both theory / research aspects as well as examples based on Apache Flink (DataStream API)
ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...Srinath Perera
DEBS Grand Challenge is a yearly, real-life data based event processing challenge posted by Distributed Event Based Systems conference. The 2015 challenge uses a taxi trip data set from New York city that includes 173 million events col- lected over the year 2013. This paper presents how we used WSO2 CEP, an open source, commercially available Complex Event Processing Engine, to solve the problem. With a 8-core commodity physical machine, our solution did about 350,000 events/second throughput with mean latency less than one millisecond for both queries. With a VirtualBox VM, our solution did about 50,000 events/second throughput with mean latency of 1 and 6 milliseconds for the first and second queries respectively. The paper will outline the solution, present results, and discuss how we optimized the solution for maximum performance.
Presentation from NORTHMOST - a new biannual series of meetings on the topic of mathematical modelling in transport.
Hosted at its.leeds.ac.uk, NORTHMOST 01 focussed on academic research, to encourage networking and collaboration between academics interested in the methodological development of mathematical modelling applied to transport.
The focus of the meetings will alternate; NORTHMOST 02 - planned for Spring 2017 - will be led by practitioners who are modelling experts. Practitioners will give presentations, with academic researchers in the audience. In addition to giving a forum for expert practitioners to meet and share best practice, a key aim of the series is to close the gap between research and practice, establishing a feedback loop to communicate the needs of practitioners to those working in university research.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
journal publishing, how to publish research paper, Call For research paper, international journal, publishing a paper, IJERD, journal of science and technology, how to get a research paper published, publishing a paper, publishing of journal, publishing of research paper, reserach and review articles, IJERD Journal, How to publish your research paper, publish research paper, open access engineering journal, Engineering journal, Mathemetics journal, Physics journal, Chemistry journal, Computer Engineering, Computer Science journal, how to submit your paper, peer reviw journal, indexed journal, reserach and review articles, engineering journal, www.ijerd.com, research journals,
yahoo journals, bing journals, International Journal of Engineering Research and Development, google journals, hard copy of journal
To maximize the value of your supply chain, you need a reliable logistics partner whose excellent support is available wherever you need it – whether that’s locally or on the other side of the world. One with a thorough depth of knowledge of your market and its dynamics, who works to the highest standards and brings you the benefit of unrivalled environmental and safety credentials, along with state-of-the art technology.
Data Natives Frankfurt v 11.0 | "Competitive advantages with knowledge graphs...Dataconomy Media
The challenges of increasing complexity of organizations, companies and projects are obvious and omnipresent. Everywhere there are connections and dependencies that are often not adequately managed or not considered at all because of a lack of technology or expertise to uncover and leverage the relationships in data and information. In his presentation, Axel Morgner talks about graph technology and knowledge graphs as indispensable building blocks for successful companies.
More Related Content
Similar to How Zalando accelerates warehouse operations with neural networks - Calvin Seward, Data Scientist at Zalando
128-Bit Area Efficient Reconfigurable Carry Select Adder ijcisjournal
Adders are one of the most critical arithmetic circuits in a system and their throughput affects the overall
performance of the system. Carry Select Adder (CSLA) is one of the fastest adders used in many dataprocessing
processors to perform fast arithmetic functions. From the structure of the CSLA, it is clear that
there is scope for reducing the area and power consumption in the CSLA. In this paper, we proposed an
area-efficient carry select adder by sharing the common Boolean logic term. After logic optimization and
sharing partial circuit, we only need one XOR gate and one inverter gate for sum generation. Through the
multiplexer, we can select the final-sum only and for carry selection we need only one AND gate and one
OR gate. Based on this modification 16-, 32-, 64-, and 128-bit CSLA architecture have been developed and
compared with the conventional CSLA architecture. The proposed design greatly reduces the area
compared to other CSLAs. From this improvement, the gate count of a 128-bit carry select adder can be
reduced from 3320 to 1664. The proposed structure is implemented in Artix-7 FPGA. Compared with the
proposed design, the conventional CSLA has 65.80% less area.
Tutorial: The Role of Event-Time Analysis Order in Data StreamingVincenzo Gulisano
Slides for our tutorial, titled “The Role of Event-Time Analysis Order in Data Streaming”, presented at the 14th ACM International Conference on Distributed and Event-Based Systems (DEBS) conference. We have recorded the tutorial, and you can find the videos at the following links:
Part 1: https://youtu.be/SW_WS6ULsdY
Part 2: https://youtu.be/bq3ECNvPwOU
You can find this slides, as well as the code examples, at https://github.com/vincenzo-gulisano/debs2020_tutorial_event_time and at SlideS
The project focuses on how Congestion Control and Queue Management techniques have evolved in the course of time and being modified to minimize packet loss and stabilize Queue length
Opensample: A Low-latency, Sampling-based Measurement Platform for Software D...Junho Suh
In this paper we propose, implement and evaluate OpenSample: a low-latency, sampling-based network measure- ment platform targeted at building faster control loops for software-defined networks. OpenSample leverages sFlow packet sampling to provide near–real-time measurements of both net- work load and individual flows. While OpenSample is useful in any context, it is particularly useful in an SDN environment where a network controller can quickly take action based on the data it provides. Using sampling for network monitoring allows OpenSample to have a 100 millisecond control loop rather than the 1–5 second control loop of prior polling-based approaches. We implement OpenSample in the Floodlight OpenFlow controller and evaluate it both in simulation and on a testbed comprised of commodity switches. When used to inform traffic engineering, OpenSample provides up to a 150% throughput improvement over both static equal-cost multi-path routing and a polling-based solution with a one second control loop.
Modified Headfirst Sliding Routing: A Time-Based Routing Scheme for Bus-Nochy...IJERA Editor
Several interesting topologies emerge by incorporating the third dimension in networks-on-chip (NoC). The Network-on-Chip (NoC) is Network-version of System on-Chip (SoC) means that on-chip communication is done through packet based networks. In NOC topology, routing algorithm and switching are main terminology .The routing algorithm is one of the key factor in NOC architecture. The routing algorithm, which defines as the path taken by a packet between the source and the destination. A good routing algorithm is necessary to improve the network performance. . Here we are proposing a new architecture to improve the throughput and latency of the network. In the proposed approach we are using a fixed path for the packet to transmit from source to destination
Crash course on data streaming (with examples using Apache Flink)Vincenzo Gulisano
These are the slides I used for a crash course (4 hours) on data streaming. It contains both theory / research aspects as well as examples based on Apache Flink (DataStream API)
ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...Srinath Perera
DEBS Grand Challenge is a yearly, real-life data based event processing challenge posted by Distributed Event Based Systems conference. The 2015 challenge uses a taxi trip data set from New York city that includes 173 million events col- lected over the year 2013. This paper presents how we used WSO2 CEP, an open source, commercially available Complex Event Processing Engine, to solve the problem. With a 8-core commodity physical machine, our solution did about 350,000 events/second throughput with mean latency less than one millisecond for both queries. With a VirtualBox VM, our solution did about 50,000 events/second throughput with mean latency of 1 and 6 milliseconds for the first and second queries respectively. The paper will outline the solution, present results, and discuss how we optimized the solution for maximum performance.
Presentation from NORTHMOST - a new biannual series of meetings on the topic of mathematical modelling in transport.
Hosted at its.leeds.ac.uk, NORTHMOST 01 focussed on academic research, to encourage networking and collaboration between academics interested in the methodological development of mathematical modelling applied to transport.
The focus of the meetings will alternate; NORTHMOST 02 - planned for Spring 2017 - will be led by practitioners who are modelling experts. Practitioners will give presentations, with academic researchers in the audience. In addition to giving a forum for expert practitioners to meet and share best practice, a key aim of the series is to close the gap between research and practice, establishing a feedback loop to communicate the needs of practitioners to those working in university research.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
journal publishing, how to publish research paper, Call For research paper, international journal, publishing a paper, IJERD, journal of science and technology, how to get a research paper published, publishing a paper, publishing of journal, publishing of research paper, reserach and review articles, IJERD Journal, How to publish your research paper, publish research paper, open access engineering journal, Engineering journal, Mathemetics journal, Physics journal, Chemistry journal, Computer Engineering, Computer Science journal, how to submit your paper, peer reviw journal, indexed journal, reserach and review articles, engineering journal, www.ijerd.com, research journals,
yahoo journals, bing journals, International Journal of Engineering Research and Development, google journals, hard copy of journal
To maximize the value of your supply chain, you need a reliable logistics partner whose excellent support is available wherever you need it – whether that’s locally or on the other side of the world. One with a thorough depth of knowledge of your market and its dynamics, who works to the highest standards and brings you the benefit of unrivalled environmental and safety credentials, along with state-of-the art technology.
Data Natives Frankfurt v 11.0 | "Competitive advantages with knowledge graphs...Dataconomy Media
The challenges of increasing complexity of organizations, companies and projects are obvious and omnipresent. Everywhere there are connections and dependencies that are often not adequately managed or not considered at all because of a lack of technology or expertise to uncover and leverage the relationships in data and information. In his presentation, Axel Morgner talks about graph technology and knowledge graphs as indispensable building blocks for successful companies.
Data Natives Munich v 12.0 | "How to be more productive with Autonomous Data ...Dataconomy Media
Every day we are challenged with more data, more use cases and an ever increasing demand for analytics. In this talk Bjorn will explain how autonomous data management and machine learning help innovators to more productive and give examples how to deliver new data driven projects with less risk at lower costs.
Data Natives meets DataRobot | "Build and deploy an anti-money laundering mo...Dataconomy Media
Compliance departments within banks and other financial institutions are turning to machine learning for improving their Anti Money Laundering compliance activities. Today, the systems that aim to detect potentially suspicious activity are commonly rule-based, and suffer from ultra-high false positive rates. DataRobot will discuss how their Automated Machine Learning platform was successfully used for a real use case to reduce their false positives and to enhance their Anti-Money Laundering activities.
Data Natives Munich v 12.0 | "Political Data Science: A tale of Fake News, So...Dataconomy Media
Trump, Brexit, Cambridge Analytica... In the last few years, we have had to confront the consequences of the use and misuse of data science algorithms in manipulating public opinion through social media. The use of private data to microtarget individuals is a daily practice (and a trillion-dollar industry), which has serious side-effects when the selling product is your political ideology. How can we cope with this new scenario?
Data Natives Vienna v 7.0 | "The Ingredients of Data Innovation" - Robbert de...Dataconomy Media
When taking a deep dive into the world of data, one thing is certain: the ultimate goal is to create something new, something better, something faster. In other words, innovation should always be at the forefront of companies strategic outlook, whether their goal is to pioneer new processes, user experiences, products or services.
Data Natives Cologne v 4.0 | "The Data Lorax: Planting the Seeds of Fairness...Dataconomy Media
What does it take to build a good data product or service? Data practitioners always think about the technology, user experience and commercial viability. But rarely do they think about the implications of the systems they build. This talk will shed light on the impact of AI systems and the unintended consequences of the use of data in different products. It will also discuss our role, as data practitioners, in planting the seeds of fairness in the systems we build.
Data Natives Cologne v 4.0 | "How People Analytics Can Reveal the Hidden Aspe...Dataconomy Media
We all hear about the power of data, big data and data analysis in todays market place. But rarely feel it's touchable effects on our own business decisions and performance.
Let's dive into it and see how can people analytics increase people performance, motivation and business revenue?
Data Natives Amsterdam v 9.0 | "Ten Little Servers: A Story of no Downtime" -...Dataconomy Media
Cloud Infrastructure is a hostile environment: a power supply failure or a network outage leads to downtime and big losses. There is nothing we can trust: a single server, a server rack, even a whole datacenter can fail, and if an application is fragile by design, disruption is inevitable. We must distribute our application and diversify cloud data strategy to survive disturbances of any scale. Apache Cassandra is a cloud-native platform-agnostic database that stores data with a distributed redundancy so it easily survives any issue. What to know how Apple and Netflix handle petabytes of data, keeping it highly available? Join us and listen to a story of 10 little servers and no downtime!
Data Natives Amsterdam v 9.0 | "Point in Time Labeling at Scale" - Timothy Th...Dataconomy Media
In the data industry, having correctly labelled datasets is vital. Timothy Thatcher explains how tagging your data while considering time and location and complex hierarchical rules at scale can be handled.
Data NativesBerlin v 20.0 | "Serving A/B experimentation platform end-to-end"...Dataconomy Media
During the lifetime of an A/B test product managers and analysts in GetYourGuide require various tools and different kinds of data to plan the trial properly, control it during the run and analyze the results at the end. This talk would be about the architecture, tools and data flow for serving their needs.
Data Natives Berlin v 20.0 | "Ten Little Servers: A Story of no Downtime" - A...Dataconomy Media
Cloud Infrastructure is a hostile environment: a power supply failure or a network outage leads to downtime and big losses. There is nothing we can trust: a single server, a server rack, even a whole datacenter can fail, and if an application is fragile by design, disruption is inevitable. We must distribute our application and diversify cloud data strategy to survive disturbances of any scale. Apache Cassandra is a cloud-native platform-agnostic database that stores data with a distributed redundancy so it easily survives any issue. What to know how Apple and Netflix handle petabytes of data, keeping it highly available? Join us and listen to a story of 10 little servers and no downtime!
Big Data Frankfurt meets Thinkport | "The Cloud as a Driver of Innovation" - ...Dataconomy Media
Creativity is the mental ability to create new ideas and designs. Innovation, on the other hand, Means developing useful solutions from new ideas. Creativity can be goal-oriented, Whereas innovation is always goal-oriented. This bedeutet, dass innovation aims to achieve defined goals. The use of cloud services and technologies promises enterprise users many benefits in terms of more flexible use of IT resources and faster access to innovative solutions. That’s why we want to examine the question in this talk, of what role cloud computing plays for innovation in companies.
Thinkport meets Frankfurt | "Financial Time Series Analysis using Wavelets" -...Dataconomy Media
Presentation of Time Series Properties of Financial Instrument and Possibilities in Frequency Decomposition and Information Extraction using FT, STFT and Wavelets with Outlook in Current Research on Wavelet Neural Networks
Big Data Helsinki v 3 | "Distributed Machine and Deep Learning at Scale with ...Dataconomy Media
"With most machine learning (ML) and deep learning (DL) frameworks, it can take hours to move data for ETL, and hours to train models. It's also hard to scale, with data sets increasingly being larger than the capacity of any single server. The amount of the data also makes it hard to incrementally test and retrain models in near real-time.
Learn how Apache Ignite and GridGain help to address limitations like ETL costs, scaling issues and Time-To-Market for the new models and help achieve near-real-time, continuous learning.
Yuriy Babak, the head of ML/DL framework development at GridGain and Apache Ignite committer, will explain how ML/DL work with Apache Ignite, and how to get started.
Topics include:
— Overview of distributed ML/DL including architecture, implementation, usage patterns, pros and cons
— Overview of Apache Ignite ML/DL, including built-in ML/DL algorithms, and how to implement your own
— Model inference with Apache Ignite, including how to train models with other libraries, like Apache Spark, and deploy them in Ignite
— How Apache Ignite and TensorFlow can be used together to build distributed DL model training and inference"
Big Data Helsinki v 3 | "Federated Learning and Privacy-preserving AI" - Oguz...Dataconomy Media
"Machine learning algorithms require significant amounts of training data which has been centralized on one machine or in a datacenter so far. For numerous applications, such need of collecting data can be extremely privacy-invasive. Recent advancements in AI research approach this issue by a new paradigm of training AI models, i.e., Federated Learning.
In federated learning, edge devices (phones, computers, cars etc.) collaboratively learn a shared AI model while keeping all the training data on device, decoupling the ability to do machine learning from the need to store the data in the cloud. From personal data perspective, this paradigm enables a way of training a model on the device without directly inspecting users’ data on a server. This talk will pinpoint several examples of AI applications benefiting from federated learning and the likely future of privacy-aware systems."
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Subhajit Sahu
Abstract — Levelwise PageRank is an alternative method of PageRank computation which decomposes the input graph into a directed acyclic block-graph of strongly connected components, and processes them in topological order, one level at a time. This enables calculation for ranks in a distributed fashion without per-iteration communication, unlike the standard method where all vertices are processed in each iteration. It however comes with a precondition of the absence of dead ends in the input graph. Here, the native non-distributed performance of Levelwise PageRank was compared against Monolithic PageRank on a CPU as well as a GPU. To ensure a fair comparison, Monolithic PageRank was also performed on a graph where vertices were split by components. Results indicate that Levelwise PageRank is about as fast as Monolithic PageRank on the CPU, but quite a bit slower on the GPU. Slowdown on the GPU is likely caused by a large submission of small workloads, and expected to be non-issue when the computation is performed on massive graphs.
Adjusting OpenMP PageRank : SHORT REPORT / NOTESSubhajit Sahu
For massive graphs that fit in RAM, but not in GPU memory, it is possible to take
advantage of a shared memory system with multiple CPUs, each with multiple cores, to
accelerate pagerank computation. If the NUMA architecture of the system is properly taken
into account with good vertex partitioning, the speedup can be significant. To take steps in
this direction, experiments are conducted to implement pagerank in OpenMP using two
different approaches, uniform and hybrid. The uniform approach runs all primitives required
for pagerank in OpenMP mode (with multiple threads). On the other hand, the hybrid
approach runs certain primitives in sequential mode (i.e., sumAt, multiply).
Adjusting primitives for graph : SHORT REPORT / NOTESSubhajit Sahu
Graph algorithms, like PageRank Compressed Sparse Row (CSR) is an adjacency-list based graph representation that is
Multiply with different modes (map)
1. Performance of sequential execution based vs OpenMP based vector multiply.
2. Comparing various launch configs for CUDA based vector multiply.
Sum with different storage types (reduce)
1. Performance of vector element sum using float vs bfloat16 as the storage type.
Sum with different modes (reduce)
1. Performance of sequential execution based vs OpenMP based vector element sum.
2. Performance of memcpy vs in-place based CUDA based vector element sum.
3. Comparing various launch configs for CUDA based vector element sum (memcpy).
4. Comparing various launch configs for CUDA based vector element sum (in-place).
Sum with in-place strategies of CUDA mode (reduce)
1. Comparing various launch configs for CUDA based vector element sum (in-place).
Techniques to optimize the pagerank algorithm usually fall in two categories. One is to try reducing the work per iteration, and the other is to try reducing the number of iterations. These goals are often at odds with one another. Skipping computation on vertices which have already converged has the potential to save iteration time. Skipping in-identical vertices, with the same in-links, helps reduce duplicate computations and thus could help reduce iteration time. Road networks often have chains which can be short-circuited before pagerank computation to improve performance. Final ranks of chain nodes can be easily calculated. This could reduce both the iteration time, and the number of iterations. If a graph has no dangling nodes, pagerank of each strongly connected component can be computed in topological order. This could help reduce the iteration time, no. of iterations, and also enable multi-iteration concurrency in pagerank computation. The combination of all of the above methods is the STICD algorithm. [sticd] For dynamic graphs, unchanged components whose ranks are unaffected can be skipped altogether.
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Data and AI
Round table discussion of vector databases, unstructured data, ai, big data, real-time, robots and Milvus.
A lively discussion with NJ Gen AI Meetup Lead, Prasad and Procure.FYI's Co-Found
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...2023240532
Quantitative data Analysis
Overview
Reliability Analysis (Cronbach Alpha)
Common Method Bias (Harman Single Factor Test)
Frequency Analysis (Demographic)
Descriptive Analysis
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...John Andrews
SlideShare Description for "Chatty Kathy - UNC Bootcamp Final Project Presentation"
Title: Chatty Kathy: Enhancing Physical Activity Among Older Adults
Description:
Discover how Chatty Kathy, an innovative project developed at the UNC Bootcamp, aims to tackle the challenge of low physical activity among older adults. Our AI-driven solution uses peer interaction to boost and sustain exercise levels, significantly improving health outcomes. This presentation covers our problem statement, the rationale behind Chatty Kathy, synthetic data and persona creation, model performance metrics, a visual demonstration of the project, and potential future developments. Join us for an insightful Q&A session to explore the potential of this groundbreaking project.
Project Team: Jay Requarth, Jana Avery, John Andrews, Dr. Dick Davis II, Nee Buntoum, Nam Yeongjin & Mat Nicholas
The affect of service quality and online reviews on customer loyalty in the E...
How Zalando accelerates warehouse operations with neural networks - Calvin Seward, Data Scientist at Zalando
1. How Zalando Accelerates Warehouse Operations with Neural
Networks
Calvin Seward
Big Data Berlin v. 6.0
28 January 2016
1 / 22
2. Outline
Picker Routing Problem
Order Batching Problem
Neural Network Estimate of Pick Route Length
Order Batch optimization via Simulated Annealing
2 / 22
3. Outline
Picker Routing Problem
Order Batching Problem
Neural Network Estimate of Pick Route Length
Order Batch optimization via Simulated Annealing
This was a project that was a collaboration between Rolland Vollgraf, Sebastian Heinz
and myself. Some of the gures have been shamelessly stolen from Roland.
2 / 22
4. Zalando's Logistics Centers
13.8 Million orders from 01.07.15 30.09.15
174,684 orders send per working day (Mo. Sa.)
Every second handling time per order requires 160 man-days of work / month
Any increase in ecency has a big impact
3 / 22
13. OCaPi Algorithm
Optimal CArt PIck
To solve picker routing problem, we
developed the OCaPi Algorithm
Calculates the optimal route to walk
Also determines optimal cart handling
strategy
Figure: The Okapi Our Mascot
12 / 22
14. OCaPi Algorithm
Optimal CArt PIck
To solve picker routing problem, we
developed the OCaPi Algorithm
Calculates the optimal route to walk
Also determines optimal cart handling
strategy
Has complexity that is linear in the
number of aisles
Figure: The Okapi Our Mascot
12 / 22
15. OCaPi Algorithm
Optimal CArt PIck
To solve picker routing problem, we
developed the OCaPi Algorithm
Calculates the optimal route to walk
Also determines optimal cart handling
strategy
Has complexity that is linear in the
number of aisles
Unfortunately still has a runtime of
around 1 second Figure: The Okapi Our Mascot
12 / 22
16. Simplied Order Batching Problem
Bipartite Graph Formulation
n Orders
o1
o2
o3
. . .
on
m Pick Tours
t1
t2
. . .
tm
17. Simplied Order Batching Problem
Bipartite Graph Formulation
n Orders
o1
o2
o3
. . .
on
m Pick Tours
t1
t2
. . .
tm
18. Simplied Order Batching Problem
Bipartite Graph Formulation
n Orders
o1
o2
o3
. . .
on
m Pick Tours
t1
t2
. . .
tm
13 / 22
20. Order Batching Problem
Brute Force Split of 10 Orders à 2 Items into Optimal Two Pick Routes → 8.3% Boost
15 / 22
21. Neural Network Estimate of Pick Route Length
This simple example could be done
with brute force
A realistic example with 40 orders à 2
items has a complexity of
40!
2 · 20! · 20!
≈ 6.9 · 1010
at 1 second per route, you'd wait 2185
years
16 / 22
22. Neural Network Estimate of Pick Route Length
This simple example could be done
with brute force
A realistic example with 40 orders à 2
items has a complexity of
40!
2 · 20! · 20!
≈ 6.9 · 1010
at 1 second per route, you'd wait 2185
years
Use clever heuristics like simulated
annealing
Estimate pick route length with Neural
Networks
16 / 22
23. Neural Network Estimate of Pick Route Length
OCaPi cost landscape
f : (N × R)n → R+
is a nice function because it is:
Lipschitz continuous in the real-valued
arguments
Piecewise linear in the real-valued arguments
Locally sensitive
17 / 22
24. Neural Network Estimate of Pick Route Length
OCaPi cost landscape
f : (N × R)n → R+
is a nice function because it is:
Lipschitz continuous in the real-valued
arguments
Piecewise linear in the real-valued arguments
Locally sensitive
Perfect function to model with Convolutional
Neural Networks with ReLUs:
˜f(x) := (W2(W1x + b1)+ + b2)+
Train convolutional neural network with 1
million examples
17 / 22
25. Neural Network Estimate of Pick Route Length
Estimation Accuracy Frequency of relative estimation error estimated travel time
calculated travel time
18 / 22
26. Neural Network Estimate of Pick Route Length
Estimation Speed Time Per Route on two Intel Xeon E5-2640 and two NVIDIA Tesla K80 accelerators
number pick lists OCaPi CPU network GPU network
1 5.369 2.202e-3 1.656e-3
10 1.326 1.991e-4 1.832e-4
100 0.365 6.548e-5 5.919e-5
1000 3.086e-5 2.961e-5
10000 2.554e-5 2.336e-5
19 / 22
27. Order Batch optimization via Simulated Annealing
Estimated and Exact Improvement in Example Simulated Annealing Run
20 / 22