#1 Resources in Deep Learning — fastai
The right kind of resource has the power to help us not only understand different concepts but also to inculcate an interest and love for the topic in question.
Our resources for today focus on deep learning and mainly include the ones developed and based on fast.ai. Fastai has been doing amazing work in the field of deep learning, from developing video tutorials to building a library that makes many deep learning-based tasks quite easy. Let us see the resources:
1. Practical Deep Learning for Coders, v3
Divided into two parts, this course takes a top-down approach to teach deep learning by explaining its various applications in different fields. What I really like about this course is that every single line of code is explained so that the learners have a clear idea of what they are coding.
2. Computational Linear Algebra
This course is focused on the question: How do we do matrix computations with acceptable speed and acceptable accuracy?
This course was taught in the University of San Francisco’s Masters of Science in Analytics program, summer 2017 (for graduate students studying to become data scientists). The course is taught in Python with Jupyter Notebooks, using libraries such as Scikit-Learn and Numpy for most lessons, as well as Numba (a library that compiles Python to C for faster performance) and PyTorch (an alternative to Numpy for the GPU) in a few lessons.
Accompanying the notebooks is a playlist of lecture videos, available on YouTube. If you are ever confused by a lecture or it goes too quickly, check out the beginning of the next video, where I review concepts from the previous lecture, often explaining things from a new perspective or with different illustrations, and answer questions.
3. The fastai book by Jeremy Howard and Sylvain Gugger
These draft notebooks cover an introduction to deep learning, fastai, and PyTorch. fastai is a layered API for deep learning; for more information, see the fastai paper.
4. A Code-First Introduction to Natural Language Processing
Our newest course is a code-first introduction to NLP, following the fast.ai teaching philosophy of sharing practical code implementations and giving students a sense of the “whole game” before delving into lower-level details. Applications covered include topic modeling, classification (identifying whether the sentiment of a review is positive or negative), language modeling, and translation. The course teaches a blend of traditional NLP topics (including regex, SVD, naive bayes, tokenization) and recent neural network approaches (including RNNs, seq2seq, attention, and the transformer architecture), as well as addressing urgent ethical issues, such as bias and disinformation. Topics can be watched in any order.
5. fast.ai Part 1, 2019 & Things Jeremy says to do
For anyone looking to revise the lectures in less than 10 minutes, this a pretty good podcast to refer to.
