GitHunt
FC

fchouteau/deep-learning

Deep Learning section of the Algorithms in Machine Learning class at ISAE-Supaero

Deep Learning

Deep Learning section of the Algorithms in Machine Learning class at ISAE-Supaero

Adapted from Emmanuel Rachelson's Machine Learning class

Syllabus

This class covers deep learning in a total of 24 hours over 5 weeks. We start
with simple multi-layer perceptrons, backpropogation, and gradient descent,
exploring at the fundamental aspects of deep learning in depth. We cover a wide
range of deep learning topics, from Natural Language Processing to Generative
Adversarial Networks; the full schedule is below. The goal is that students
understand the capacities of deep learning, the current state of the field, and
the challenges of using and developing deep learning algorithms. By the end of
this class, we expect students that students will be able to understand recent
literature in deep learning, implement novel neural network architectures, use
and understand the PyTorch library in many ways, and apply deep learning to
different domains.

2020 Schedule

Schedule
17/11 Artificial Neural Networks ANNs, backpropagation, Stochastic Gradient Descent
23/11 Deep Learning layers, convolution, architectures, training
30/11 Deep Learning for Computer Vision, pt 1 Convolutional Neural Networks, satellite imagery
01/12 Deep Learning for Computer Vision, pt 2
07/12 RNNs Recurrent Neural Networks, LSTM, GRU
08/12 NLP Natural Language Processing, Transformers
15/12 GANs Generative Adversarial Networks, CycleGAN
16/12 Dimensionality Reduction Autoencoders, t-SNE

Languages

Jupyter Notebook99.2%Python0.5%CSS0.2%HTML0.1%Makefile0.0%Shell0.0%

Contributors

Other
Created November 22, 2020
Updated November 30, 2021
fchouteau/deep-learning | GitHunt