Click here for the webpage for Fall 2019.

- This is a tentative class outline and is subject to change throughout the semester.
- Slides will be finalized after each lecture.

Event Type | Date | Description | Course Materials |
---|---|---|---|

Lecture | Tuesday, Jan. 23 | Intro to Deep Learning, historical context. |
[slides] [python/numpy tutorial] [jupyter tutorial] |

Lecture | Thursday, Jan. 25 | Image classification and the data-driven approach k-nearest neighbor Linear classification |
[slides] [image classification notes] [linear classification notes] |

Optional Discussion | Friday, Jan. 26 | No discussion section | |

Lecture | Tuesday, Jan. 30 | Loss functions |
[slides] |

Lecture | Thursday, Feb. 1 | Optimization: Stochastic Gradient Descent and Backpropagation |
[slides] [optimization notes] |

Optional Discussion | Friday, Feb. 2 | Slicing and broadcasting in Python | |

Lecture | Tuesday, Feb. 6 | Backpropagation & Neural Networks I |
[slides] [backprop notes] [Efficient BackProp] (optional) related: [1], [2], [3] (optional) |

Lecture | Thursday, Feb. 8 |
Neural Networks II Higher-level representations, image features Vector, Matrix, and Tensor Derivatives |
[slides] handout 1: Vector, Matrix, and Tensor Derivatives handout 2: Derivatives, Backpropagation, and Vectorization Deep Learning [Nature] (optional) |

Optional Discussion | Friday, Feb. 9 | Reviewing the chain rule, applying the chain rule to vectors | |

Lecture | Tuesday, Feb. 13 | Neural Networks III |
[slides] tips/tricks: [1], [2] (optional) |

Lecture | Thursday, Feb. 15 |
Training Neural Networks I: Activation Functions |
[slides] [Neural Nets notes 1] |

Optional Discussion | Friday, Feb. 16 | No discussion section | |

Lecture | Tuesday, Feb. 20 |
Training Neural Networks II: weight initialization, batch normalization |
[slides] [Neural Nets notes 2] [Batch Norm] Copula Normalization (optional) |

Lecture | Thursday, Feb. 22 |
Training Neural Network III: babysitting the learning process, hyperparameter optimization |
[slides] [Bengio 2012] (optional) |

Optional Discussion | Friday, Feb. 23 | A closer look at the maths inside batch normalization | |

Lecture | Tuesday, Feb. 27 |
Training Neural Network III: babysitting the learning process, hyperparameter optimization Training Neural Network IV: model ensembles, dropout |
[slides] [slides] [Neural Nets notes 3] LeNet (optional) |

Lecture | Thursday, Mar. 1 |
Training Neural Network V: parameter updates Convolutional Neural Networks: convolution layer, pooling layer, fully connected layer |
[slides] [slides] |

Optional Discussion | Friday, Mar. 2 | Convolutional neural networks | [slides] |

Lecture | Tuesday, Mar. 6 |
Convolutional Neural Networks: (cont.) convolution layer, pooling layer, fully connected layer |
[slides] |

Lecture | Thursday, Mar. 8 |
ConvNets for spatial localization, Object detection Final project information |
[slides] [slides] [Stanford cs231n project reports] [2016 Fall project reports] |

Optional Discussion | Friday, Mar. 9 | No discussion section | |

No class | Tuesday, Mar. 13 | Spring break | |

No class | Thursday, Mar. 15 | Spring break | |

No discussion | Friday, Mar. 16 | Spring break | |

Lecture | Tuesday, Mar. 20 | ConvNets for spatial localization, Object detection |
[slides] |

Lecture | Thursday, Mar. 22 | ConvNets for spatial localization, Object detection (cont.) |
[slides] FCN |

Optional Discussion | Friday, Mar. 23 | Midterm review | |

Midterm | Tuesday, Mar. 27 | In-class midterm | |

Lecture | Thursday, Mar. 29 | ConvNets for spatial localization, Object detection (cont.) | |

Optional Discussion | Friday, Mar. 30 | No discussion section | |

Lecture | Tuesday, Apr. 3 |
Understanding and visualizing Convolutional Neural Networks Backprop into image: Visualizations, deep dream |
[slides] [visualization notes] |

Lecture | Thursday, Apr. 5 |
Understanding and visualizing Convolutional Neural Networks (cont.) Backprop into image: Visualizations, deep dream (cont.) |
[slides] [visualization notes] |

Optional Discussion | Friday, Apr. 6 | Go through midterm problems | |

Lecture | Tuesday, Apr. 10 |
Artistic style transfer Adversarial fooling examples Recurrent Neural Networks (RNN) |
[slides] DL book RNN chapter (optional) min-char-rnn, char-rnn, neuraltalk2 |

Lecture | Thurday, Apr. 12 |
Recurrent Neural Networks (RNN) (cont.) Long Short Term Memory (LSTM) |
[slides] (cont.) The Unreasonable Effectiveness of RNN (optional) Understanding LSTM Networks (optional) |

Optional Discussion | Friday, Apr. 13 | Review of RMM, LSTM, Adversarial examples, Visualization | |

No class | Tuesday, Apr. 17 | Monday class schedule will be followed (Patriot's Day: Monday, Apr. 16) | |

Lecture | Thursday, Apr. 19 | Training ConvNets in practice |
[slides] |

Optional Discussion | Friday, Apr. 20 | No discussion section | |

Lecture | Tuesday, Apr. 24 | TBD | |

Lecture | Thursday, Apr. 26 | TBD | |

Optional Discussion | Friday, Apr. 27 | No discussion section | |

Presentation | Tuesday, May 1 |
Poster presentations Two sessions, both at CS150/151: 8-10am (regular time) 12-2:30pm |