近期在网路上看到一个深度学习的课程,由dataflowr的一个组织推出的课程
《Hands-on tour to deep learning with PyTorch》
主要的学习路径如下:
Day 1:
(slides) introductory slides
(code) a first example on Colab: dogs and cats with VGG
(code) making a regression with autograd: intro to pytorch
Day 2:
(slides) refresher: linear/logistic regressions, classification and PyTorch module.
(code) understanding convolutions and your first neural network for a digit recognizer.
(slides) embeddings and dataloader
(code) Collaborative filtering: matrix factorization and recommender system
(slides) Variational Autoencoder by Stéphane
(code) AE and VAE
Day 3:
(slides) Towards deep learning for the real world by Andrei
(code) softmax temperature; Mixture Density Networks; Bayes by backpropagation
(slides) Generative Adversarial Networks
(code) Conditional and Info GANs
Day 4:
Reccurrent Neural Networks: slides and associated code
(code) PyTorch tutorial on char-RNN
(code) Word2vec
(code) Playing with word embedding
Structured Self-attentive Sentence Embedding papercode to obtain Glove NLP mini-project
Day 5:
(slides) Opening the black box
(code) CAM
(code) Adversarial examples
Graph Neural Networks by Timothée
课程地址:https://mlelarge.github.io/dataflowr-web/cea_edf_inria.html
代码地址:https://github.com/mlelarge/dataflowr