11. / AI - 11
Training a prediction machine by
showing examples instead of
programming it.
-Yann LeCun
(prediction machine: )
12. / AI - 12
Find the common patterns
from the left waveforms
It seems impossible to write
a program for speech
recognition
You quickly get lost in the
exceptions and special cases.
(Slide Credit: Hung-Yi Lee)
13. / AI -
You said
“ ”
(Slide Credit: Hung-Yi Lee)
38. 0.95
F-score
Algorithm Ophthalmologist
(median)
0.91
“The study by Gulshan and colleagues
truly represents the brave new world in
medicine.”
“Google just published this paper in JAMA
(impact factor 44.405) [...] It actually lives
up to the hype.”
Dr. Andrew Beam, Dr. Isaac
Kohane Harvard Medical School
Dr. Luke Oakden-Rayner
University of Adelaide
39. /
Deep Learning for Detection of Diabetic Eye Disease
39
Algorithm’s F1-score: 0.95
Median F1-score of 8 ophthalmologists : 0.91
48. / 48
Deep Learning for Kidney Function Classification and
Prediction using Ultrasound-based Imaging
Chin-Chi Kuo1, Chun-Min Chang2, Kuan-Ting Liu2,Wei-Kai Lin2,
Chih-Wei Chung1, and Kuan-Ta Chen2
1Big Data Center, China Medical University Hospital, China Medical University,Taichung,Taiwan
2Institute of Information Science,Academia Sinica,Taiwan
eGFR
( )
51. Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
51
Goal: diagnose irregular heart rhythms, also known as
arrhythmias, from single-lead ECG signals better than a
cardiologist
52. /
Input and Output
Input: a time-series of raw ECG signal
The 30 second long ECG signal is sampled at 200 Hz
From 29,163 patients
Output: a sequence of rhythm classes
The model outputs a new prediction once every second
Total 14 rhythm classes are identified
52
54. /
Model
34 layers NN
16 residual blocks
2 conv layers per block
Filter length = 16 samples
# filter = 64*k, k start from 1 and is
incremented every 4-th residual block
Every residual block subsamples
its input by a factor of 2
54
62. Predictive tasks for healthcare
Given a large corpus of training data of de-identified medical records, can we
predict interesting aspects of the future for a patient not in the training set?
! will patient be readmitted to hospital in next N days?
! what is the likely length of hospital stay for patient checking in?
! what are the most likely diagnoses for the patient right now? and
why?
! what medications should a doctor consider prescribing?
! what tests should be considered for this patient?
! which patients are at highest risk for X in next month?
Collaborating with several healthcare organizations, including UCSF,
Stanford, and Univ. of Chicago. Have early promising results.
72. /
(Moravec’s Paradox)
High cognitive processes
Conscious processes
Chesses, math, problem solving
Difficult for humans
Easy for computers
Low Cognitive processes
Perception, action, fight/flight
responses, social interactions
Easy for humans
Difficult for computers
72
77. /
Strong AI Weak AI
Can think
Own conscious
Act as it can think
Consciousless
(1980)
78. /
What we can and cannot today
What we can have
Safer car, autonomous car
Better medical image analysis
Personalized medicine
Adequate language translation
Useful but stupid chatbots
Information search, retrieval,
filtering
Numerous applications in energy,
finance, manufacturing, commerce,
law, …
What we cannot have (yet)
Machine with common sense
Intelligent personal assistants
“Smart” chatbots
Household robots
Agile and dexterous robots
Artificial General Intelligence (AGI)
78
(Credit:Yann LeCun)
83. /
AI Don’t Know What They are Talking About
83
https://www.facebook.com/playgroundenglish/videos/629372370729430/?
hc_ref=ARQHCaS2GZ9jUgZermEupF5yerADq2X9F9P40OR3n70poUiCy7R0X3oHrGxyL
SrWVdI
84. Change is the only constant.
- Heraclitus (535 BC - 475 BC)
(Slide Credit:Albert Chen)