August 2-20, 2021
Objectives: Gain hands-on, code-first experience with deep learning theories, models, and skills that are useful for applications and for advancing science. We focus on how to decide which problems can be tackled with deep learning, how to determine what model is best, how to best implement a model, how to visualize / justify findings, and how neuroscience can inspire deep learning. And throughout we emphasize the ethical use of DL.
Please check out expected prerequisites here!
Confirmed speakers:
- Aude Oliva (MIT)
- Yoshua Bengio (MILA)
- Yann LeCun (Facebook)
- Melanie Mitchell (Portland State U)
- Kyunghyun Cho (NYU)
- Chelsea Finn (Stanford)
- Amita Kapoor (U Delhi)
- Emily Denton (Google)
- Joao Sedoc (NYU)
- Anima Anandkumar (Caltech)
Coming soon... stay tuned...
coordinated by Konrad Kording (U Penn)
Description Welcome, introduction to Google Colab, meet and greet, a bit of DL history, DL basics and introduction to Pytorch
coordinated by Andrew Saxe (Oxford)
Description Gradients, AutoGrad, linear regression, concept of optimization, loss functions, designing deep linear systems and how to train them
coordinated by Surya Ganguli (Stanford)
Description From neuroscience inspiration, to solving the XOR problem, to function approximation, cross-validation, training, and trade-offs
coordinated by Ioannis Mitliagkas (MILA)
Description Why optimization is hard and all the tricks to get it to work
coordinated by Lyle Ungar (U Penn)
Description The problem of overfitting and different ways to solve it
coordinated by Alona Fyshe (U Alberta)
Description How the number of parameters affects generalization, and what Convolutional Neural Networks (Convnets) and Recurrent Neural Networks (RNNs) can do for you to help
coordinated by Alexander Ecker (U Goettingen)
Description Modern Convolutional Neural Nets and how to use them for Transfer Learning
coordinated by James Evans (DeepAI)
Description Memory, time series, recurrence, vanishing gradients and embeddings
coordinated by He He (NYU)
Description How attention helps classification, encoding and decoding
coordinated by Vikash Gilja (UCSD) and Akash Srivastava (MIT-IBM)
Description Variational Auto-Encoders (VAEs) and Generative Adversarial Networks (GANs) as methods for representing latent data statistics
coordinated by Blake Richards (McGill) and Tim Lillicrap (Google DeepMind)
Description Learning without direct supervision
coordinated by Jane Wang (Google DeepMind)
Description How RL can help solve DL problems
coordinated by Tim Lillicrap (Google DeepMind) and Blake Richards (McGill)
Description Get to learn how RL solved the game of Go
coordinated by Joshua T. Vogelstein (Johns Hopkins) and Vincenzo Lomonaco (U Pisa)
Description How can we get a causality, how to generalize out of sample, what will the future bring?
coordinated by The NMA-DL Team
Description This day is dedicated to group projects and celebrating course completion