Neural Networks: A Primer
summary
Primer that turns hand‑wavy ML talk into working knobs: shows a five-line perceptron implementation, explains feature scaling, weight matrices, backprop with gradient descent and stochastic variants, and why you can’t brute‑force weights. Demonstrates image classification (AlexNet via Caffe) running on an Intel Neural Compute Stick with 95 ms inference versus ~1–2 s on a VM. Recommends Python + numpy, pandas, scikit‑learn, TensorFlow/Keras and a Docker image called deeper; cites brain ≈1 exaflop and DNA ≈150 ZB as context.
AI-written summary · about
chapters (14)
- 0:00Introduction
- 0:32About Rishal
- 2:48What is AI
- 7:53Intelligence
- 10:26Machine Learning
- 12:39Steps in Machine Learning
- 15:22Neural Networks History
- 18:16How Neurons Work
- 22:59Neural Network Example
- 27:48Neural Network Inputs
- 35:04Data Types
- 38:12Training
- 48:14Recap
- 55:17Code
related talks
58mNeural Networks: A Primer
44mMachine Learning Exposed
43mA Gentle Introduction to Neural Networks
27mDemystifying Deep Neural Networks
54mNeural networks by example
40mNeural Networks: Where do I start?!?
54mIntroduction to Understanding Deep Learning
26mMachine Learning in the Browser with Deep Neural Networks