In 2011, a misclassification rate of 25% was near state of the art on ILSVRC
In 2012, Geoff Hinton and two graduate students, Alex Krizhevsky and Ilya Sutskever, entered ILSVRC with one of the first deep neural networks trained on GPUs, now known as "Alexnet"
Result: An error rate of 16%, nearly half what the second place entry was able to achieve.
The computer vision world immediately took notice
Several key advancements have enabled the modern deep learning revolution
Massive Data
Several key advancements have enabled the modern deep learning revolution
GPUs/CPUs
Several key advancements have enabled the modern deep learning revolution
Methodological advancements have made deeper networks easier to train
Architecture
Optimizers
Activation Functions
Several key advancements have enabled the modern deep learning revolution
Open source framework
Scikit learn -> Classic AI
Tensorflow -> Deep Learning
MNIST
Data
Model
Verify
Training
Company
Billy
Ai
Manager A
manager B
Rugu
Siva
CEO
0.8
1.2
0.7
1.1
2
0.8
0.8
1.1
1.1
0.9
3
5
Company
Billy
Ai
Manager A
Manager B
Rugu
Siva
CEO
0.8
1.2
0.7
1.1
2
0.8
0.8
1.1
1.1
0.9
3
2
(2*0.8)+(1.2*0.8) >
3 ?
(0.8*0.7)+(1.1*1.1) > 2 ?
(2.56*1.1)+(1.77*0.9) > 4 ?Yes or No
4
1+1 = 2
Traditional Computer
1+1 = 2
AI Computer
1+3 = 4
2+3 = 5
:
10+10 = 20
So they provided different way of how to use computer
https://www.microsoft.com/en-us/research/wp-content/uploads/2017/03/main.pdf