99 Machine Learning Made Easy: description,
           (The basic math needed to understand machine learning)

Invited 1.5hr Talk on Youtube
Magic, Overview, Training Data, Machine, Error Surface, Learning, Gradient Descent, Generalizing, Singularity
EECS2001 Topics
00 94 88
01 32 Overview
02 33 Generalizing from Training Data
03 16 Linear Regression, Neural Networks 1
04 14 Neural Networks 2
05 30 Matrix Multiplication
06 16 Error
07 3 Compression Example
08 14 Gradient Descent, Steepest Direction
09 1:40 Review
WATCH ABOVE by Monday Nov 15 4pm.
30 hr course in Cameroon: (videos)
Ethics: (slides)
What is machine learning and why care?
Positive effects on the average person?
Negative effects on the average person?
Will AI machines be replacing humans any time soon?
How capable is AI as a judge?
What are your thoughts on social media?
Loosing our jobs to machines?
How is the ``software'' of a neural net produced.
More Advanced Topics
Practical Considerations
Back Propagation
Convolutional, Recurrent
Generative Adversarial Networks
Reinforcement Learning Markoff Chains
Bayesian Inference
Decision Trees, Clustering
Maximum Likelihood
Dimension Reduction
Generalizing from Training Data
VC-Dimension, Sigmoid, Singularity
TEST 5: Thur Nov 25 8:00am- Fri 11:00am, with partner
TEST 6: Wed Dec 8 8:00am- Thur 11:00am, with partner

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.