Machine Learning Exposed: The Fundamentals
summary
Quick, practical tour of basics: defines supervised, unsupervised and reinforcement learning, shows the Iris dataset and an XOR demo that runs a small neural net and visualizes changing weights, explains feed-forward math (weights, biases, activation functions) and how those numbers come from backpropagation and gradient descent, demonstrates dimensionality tools like the TensorFlow embedding projector and TensorFlow Playground, and shows a Java/Spring front end that visualizes training, epochs, learning rate and hyperparameter effects.
AI-written summary · about
chapters (18)
- 0:00Introduction
- 1:45About Pivotal
- 2:21About Andrew Aang
- 5:16What is Machine Learning
- 6:19Supervised Learning
- 8:56Unsupervised Learning
- 9:34Reinforcement Learning
- 10:39Hello World Dataset
- 16:27Visual Neural Net Server
- 21:39Feedforward
- 26:08BackPropagation
- 28:04Measuring Error
- 30:48Theta
- 34:13Two Degrees of Freedom
- 35:42Make Your Own Neural Networks
- 39:09Deep Learning for J
- 40:26Playground
- 46:55Convolutional Networks
related talks
51mMachine Learning Exposed Introduction to Machine Learning
51mMachine Learning Exposed Deep and Reinforcement Learning
49mMachine Learning Exposed: Introduction to Machine Learning
44mMachine Learning Exposed
40mNeural Networks: Where do I start?!?
26mHow Machine Learning Can Help
26mMachine Learning in the Browser with Deep Neural Networks
55mTensorflow: Learning Machines