|
|
Course Material Overview
The class is divided into
two exams, one final project, and three projects.
(no final exam).
|
|
Topic
|
Exam
|
Proj
|
On-Line
Lectures
|
Boards
|
|
Week 1
|
Course Overview
|
|
|
Introduction
Initial history of NN
History of NN
ODE basics
Matrix ODEs
|
|
|
Week 2
|
Introduction to Circuits,
ODEs, and Neuroscience
|
|
|
NN -- Neurons
NN & Current
Neuron Membrane
Bio & FET Channel
FET Bio Channel
Linear Elements
Circuit Anal
1st Circuits Dynamics
HighPass 1st Order
Energy Eff and Phys Compu
Intro to Phys Compute
|
|
|
Week 3
|
Adaptive Filters
|
|
|
Adapt Filt I
Adapt Filt II
Adapt Filt III
|
1,
2,
3,
4,
5,
6,
7,
8,
9,
|
|
Week 4
|
Hopfield Networks
Original Paper (1982)
Solving TSP (1985)
|
|
June 8:
Proj 1
|
Nonlinear f( )
Hopfield I
R-C, Gm-C
Multiplication: V controlled I source
|
1,
2,
3,
4,
5,
6,
|
|
Week 5
|
Unsupervised Learning I
Oja Learning Algorithm (1982)
|
|
|
Unsupervised I
Oja's Rule
|
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
|
|
Week 6
|
Self Organizing Maps
(2013)
Vector Quantitization (VQ)
Winner-Take-All (WTA) Networks
(Lazzaro 1988)
Universal Approximator & WTA
(Mass 2000)
Visual Attention
(1998)
|
|
June 22:
Proj 2
|
|
1,
2,
3,
4,
5,
6,
7,
8,
|
|
Week 7
|
|
|
|
|
1,
2,
3,
4,
5,
|
|
Week 8
|
NN Operation
NN Generalization
|
|
July 6:
Proj 3
|
|
1,
2,
3,
4,
5,
6,
7,
|
|
Week 9
|
Exam Prep
|
July 12
|
|
|
|
1,
2,
3,
4,
5,
6
7
8
9
10
11
|
|
Week 10
|
Generative Adversarial Networks
(GAN, 2014)
|
|
July 20:
Proj 4
|
|
1,
2,
3,
4,
5,
|
|
Week 11
|
|
|
|
|
|
|
Week 12
|
Final Project
|
|
|
|
|
|
Projects are due on
Thursdays, submitted electronically by 11:59pm Metz time
Final Projects is due on
( ),
submitted electronically by 11:59pm Metz time
Additional Material:
-
Datasets: A set of MATLAB datasets for Deep Learning.
A link in the table to the main page gives the copy command to run the example file.
-
What is a neural network?
Chapter 1, Deep learning
https://youtu.be/aircAruvnKk
NN Playground from Google.
A useful visualization of a simple NN structure.
Additional circuit related material
FIR Implement
Step & Impulse
Convolution Intro
Convolution 01
Convolution 02
Freq. Resp. I
|
