epdavid1 / deep-learning-experiments

Videos, notes and experiments to understand deep learning

Deep Learning Lecture Notes and Experiments

2022 Version (Latest)

Welcome to the 2022 version of Deep Learning course. We made major changes in the coverage and delivery of this course to reflect the recent advances in the field.

Install

Assuming you already have anaconda or venv, install the required python packages to run the experiments in this version.

pip install -r requirements.txt

Coverage:

AI, ML and Deep Learning	Note	Video	Code
Overview	PDF	YouTube	-
Toolkit
Development Environment     and Code Editor	PDF	YouTube	-
Python	PDF	YouTube	-
Numpy	PDF	YouTube	Jupyter
Einsum	PDF	YouTube	Jupyter
Einops	PDF	YouTube	Jupyter
PyTorch & Timm	PDF	YouTube	PyTorch/Timm & Input Jupyter
Gradio & Hugging Face	PDF	YouTube	Jupyter
Weights and Biases	PDF	YouTube	Jupyter
Hugging Face Accelerator	Same as W&B	Same as W&B	Jupyter & Python
Datasets & Dataloaders	PDF	YouTube	Jupyter
Supervised Learning	PDF	YouTube
PyTorch Lightning	PDF	YouTube	MNIST & KWS
Keyword Spotting App			cd versions/2022/supervised/python && python3 kws-infer.py --gui
Building blocks: MLPs, CNNs, RNNs, Transformers
MLP	PDF	YouTube	MLP on CIFAR10
CNN	PDF	YouTube	CNN on CIFAR10
Transformer	PDF	YouTube	Transformer on CIFAR10
Backpropagation	Soon
Optimization	Soon
Regularization	Soon
Unsupervised Learning	Soon
AutoEncoders	PDF	YouTube	AE MNIST Colorization CIFAR10
Variational AutoEncoders	Soon
Practical Applications: Vision, Speech, NLP	Soon

What is new in 2022 version:

1. Emphasis on tools to use and deploy deep learning models. In the past, we learn how to build and train models to perform certain tasks. However, often times we want to use a pre-trained model for immediate deployment. testing or demonstration. Hence, we will use tools such as huggingface, gradio and streamlit in our discussions.

2. Emphasis on understanding deep learning building blocks. The ability to build, train and test models is important. However, when we want to optimize and deploy a deep learning model on a new hardware or run it on production, we need an in-depth understanding of the code implementation of our algorithms. Hence, there will be emphasis on low-level algorithms and their code implementations.

3. Emphasis on practical applications. Deep learning can do a lot more than recognition. Hence, we will highlight practical applications in vision (detection, segmentation), speech (ASR, TTS) and text (sentiment, summarization).

4. Various levels of abstraction. We will present deep learning concepts from low-level numpy and einops, to mid-level framework such as PyTorch, and to high-level APIs such as huggingface, gradio and streamlit. This enables us to use deep learning principles depending on the problem constraints.

5. Emphasis on individual presentation of assignments, machine exercises and projects. Online learning is hard. To maximize student learning, this course focuses on exchange of ideas to ensure individual student progress.

Star, Fork, Cite

If you find this work useful, please give it a star, fork, or cite:

@misc{atienza2020dl,
  title={Deep Learning Lecture Notes},
  author={Atienza, Rowel},
  year={2020},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/roatienza/Deep-Learning-Experiments}},
}