Ten Steps to Keras
summary
Ten Jupyter notebooks walk through concrete Keras code: ten Jupyter Notebooks show building an MLP, CNN, RNN, transfer learning and fine‑tuning, ResNets, autoencoders/adversarials, multi‑modal nets, custom layers and optimizers, and callbacks. Code runs on Keras 2 with TensorFlow/Theano backends, demonstrates tensorboard, early stopping, batch sizes, and GPU notes, and prints live numbers (for example ~88% validation on MNIST after two epochs). All notebooks and runnable examples live on the GitHub branch named pilot London 2017.
AI-written summary · about
chapters (17)
- 0:00Keras tutorial intro
- 1:01Setting up the environment and requirements
- 8:40First Keras example
- 16:12Theano vs TensorFlow basics
- 23:01Building a Keras model
- 29:48Backend and layers config
- 38:44Training and evaluation
- 44:32Custom Keras backend
- 55:43Deep learning frameworks
- 57:54MNIST dataset
- 1:00:09Multi-layer network
- 1:12:26Dropout and callbacks
- 1:16:56Dropout layers
- 1:23:05Early stopping
- 1:27:05Neural network layers
- 1:34:19Visualizing features
- 1:35:03Summary and resources
related talks
01h 29mHands-on introduction to Deep Learning with Keras and Tensorflow
37mCode First, Math Later: Learning Neural Nets Through Implementation and Examples
01h 14mKeras (3) for the Curious and Creative
43m: Shortcut to AI mastery
35mDeconstructing Deep Learning
01h 30mIntroduction to Deep Learning & Natural Language Processing
45mThe most soft and fluffy intro into Machine Learning and Deep Neural Networks
01h 57mUsing CNTKs Python Interface for Deep Learning