Lecture 1 Part 1
Lecture 1 Part 1
Computer Vision
Lecture 1: Introduction
2016
2017 2020
Machine Learning
Computer
Vision
Machine Learning
Computer Deep
Vision Learning
Machine Learning
Computer Deep
Vision Learning
Machine Learning
Computer Deep
Vision Learning
n g u age
atu ral La ing
N ss
Proce
Machine Learning
Computer Deep
Vision Learning
n g u age
ral La ing e e ch
u p
Nat ss S ition
Proce Reco
g n
Rob
o tics Machine Learning
Computer Deep
Vision Learning
n g u age
ral La ing e e ch
u p
Nat ss S ition
Proce Reco
g n
Neuroscience
Rob
o tics Machine Learning
Computer Deep
Vision Learning
Computer
Science
n g u age
ral La ing e e ch
u p
Nat ss S ition
Proce Reco
g n
Physics Psychology
Biology Slide inspiration: Justin Johnson
• CS231n overview
Leonardo da Vinci,
16th Century AD
This work is in the public domain
Left to right:
Image is free to use
Image is CC0 1.0 public
domain
Image by NASA is licensed
under CC BY 2.0
Image is CC0 1.0 public
domain
Simple cells:
Response to specific
rotation and orientation
Complex cells:
Response to light
orientation and
Cat image by CNX OpenStax is licensed movement, some
under CC BY 4.0; changes made
translation invariance
1959
Hubel & Wiesel
Response Stimulus
No
response
Slide inspiration: Justin Johnson
(a) Original picture (b) Differentiated picture (c) Feature points selected
1959 1963
Hubel & Wiesel Roberts
Lawrence Gilman Roberts, “Machine Perception of Three-Dimensional Solids”, 1963 Slide inspiration: Justin Johnson
This image is CC0 1.0 public domain This image is CC0 1.0 public domain
1959
1963 1970s 1979 1986
Hubel &
Roberts David Marr Gen. Cylinders Canny
Wiesel
AI Winter
Left Image is CC BY 3.0 Middl Image is public Right Image is CC-BY 2.0; changes made Slide inspiration: Justin Johnson
domain
Left Image is CC BY 3.0 Middl Image is public Right Image is CC-BY 2.0; changes made Slide inspiration: Justin Johnson
domain
1959
Hubel & Wiesel
1963
Roberts
1970s
David Marr
1979
Gen. Cylinders
1986
Canny
1997
Norm. Cuts
1999
SIFT
SIFT, David
Lowe, 1999
AI Winter
AI Winter
Train
Person
Airplane
1959 1963 1970s 1979 1986 1997 1999 2001 2004, 2007
Caltech101;
Hubel & Wiesel Roberts David Marr Gen. Cylinders Canny Norm. Cuts SIFT V&J PASCAL
AI Winter
AI Winter
1958
Perceptron Slide inspiration: Justin Johnson
0 1 1
1 0 1
1 1 0
x
AI Winter
1958 1969
Perceptron Minsky & Papert Slide inspiration: Justin Johnson
AI Winter
1958 1969 1980
Perceptron Minsky & Papert Neocognitron Slide inspiration: Justin Johnson
Successfully trained
perceptrons with
multiple layers Illustration of Rum elhart et al., 1986 by Lane M cIntosh,
copyright CS231n 2017
1959 1963 1970s 1979 1986 1997 1999 2001 2004, 2007
Caltech101;
Hubel & Wiesel Roberts David Marr Gen. Cylinders Canny Norm. Cuts SIFT V&J PASCAL
AI Winter
1958 1969 1980 1985
Perceptron Minsky & Papert Neocognitron Backprop Slide inspiration: Justin Johnson
1959 1963 1970s 1979 1986 1997 1999 2001 2004, 2007
Caltech101;
Hubel & Wiesel Roberts David Marr Gen. Cylinders Canny Norm. Cuts SIFT V&J PASCAL
AI Winter
1958 1969 1980 1985 1998
Perceptron Minsky & Papert Neocognitron Backprop LeNet Slide inspiration: Justin Johnson
AI Winter
1958 1969 1980 1985 1998 2006
Perceptron Minsky & Papert Neocognitron Backprop LeNet Deep Learning
AI Winter
1958 1969 1980 1985 1998 2006
Perceptron Minsky & Papert Neocognitron Backprop LeNet Deep Learning
1959 1963 1970s 1979 1986 1997 1999 2001 2004, 2007 2009
Caltech101;
Hubel & Wiesel Roberts David Marr Gen. Cylinders Canny Norm. Cuts SIFT V&J PASCAL ImageNet
AI Winter
1958 1969 1980 1985 1998 2006
Perceptron Minsky & Papert Neocognitron Backprop LeNet Deep Learning
AI Winter
1958 1969 1980 1985 1998 2006
Perceptron Minsky & Papert Neocognitron Backprop LeNet Deep Learning
1959 1963 1970s 1979 1986 1997 1999 2001 2004, 2007 2009
Caltech101;
Hubel & Wiesel Roberts David Marr Gen. Cylinders Canny Norm. Cuts SIFT V&J PASCAL ImageNet
AI Winter
1958 1969 1980 1985 1998 2006 2012
Perceptron Minsky & Papert Neocognitron Backprop LeNet Deep Learning AlexNet
1959 1963 1970s 1979 1986 1997 1999 2001 2004, 2007 2009
Caltech101;
Hubel & Wiesel Roberts David Marr Gen. Cylinders Canny Norm. Cuts SIFT V&J PASCAL ImageNet
AI Winter
1958 1969 1980 1985 1998 2006 2012
Perceptron Minsky & Papert Neocognitron Backprop LeNet Deep Learning AlexNet
AI Winter
1958 1969 1980 1985 1998 2006 2012
Perceptron Minsky & Papert Neocognitron Backprop LeNet Deep Learning AlexNet
AI Winter
1958 1969 1980 1985 1998 2006 2012
Perceptron Minsky & Papert Neocognitron Backprop LeNet Deep Learning AlexNet
fc-4096
fc-4096
fc-1000
softmax
taller than
person person
left of
wear on wear
0
Jan-04 Jul-05 Jan-07 Jul-08 Jan-10 Jul-11 Jan-13 Jul-14 Jan-16 Jul-17 Jan-19 Jul-20
Fei-Fei Li & Ehsan Adeli CS231n: Lecture 1 - 61 April 2, 2024
GFLOP per Dollar
CPU GPU (FP32) GPU (Tensor Core)
200 Recent GPUs have
“Tensor Cores”:
Special hardware
150
for deep learning!
100
0
Jan-04 Jul-05 Jan-07 Jul-08 Jan-10 Jul-11 Jan-13 Jul-14 Jan-16 Jul-17 Jan-19 Jul-20
Fei-Fei Li & Ehsan Adeli CS231n: Lecture 1 - 62 April 2, 2024
AI’s Explosive Growth & Impact
Barocas et al, “The Problem With Bias: Allocative Versus Representational Harms in Machine Learning”, SIGCIS 2017
Kate Crawford, “The Trouble with Bias”, NeurIPS 2017 Keynote Source: https://www.washingtonpost.com/technology/2019/10/22/ai-hiring-face-scanning-algorithm-increasingly-decides-whether-you-deserve-job/
Source: https://twitter.com/jackyalcine/status/615329515909156865 (2015) https://www.hirevue.com/platform/online-video-interviewing-software
Example Credit: Timnit Gebru
• CS231n overview