ΑΙhub.org
 

fast.ai release new courses and more

by
04 September 2020



share this:
Online course

Have you been thinking about getting up to speed with deep learning or applied data ethics? Well, look no further than the latest free courses from fast.ai.

Fast.ai recently announced some exciting new releases. Here is their full list of available courses:

Practical deep learning for coders

This course covers the following topics:

  • How to train models that achieve state-of-the-art results in computer vision, natural language processing (NLP), tabular data and collaborative filtering.
  • How to turn models into web applications, and deploy them
  • Why and how deep learning models work, and how to use that knowledge to improve the accuracy, speed, and reliability of models
  • The latest deep learning techniques that really matter in practice
  • How to implement stochastic gradient descent and a complete training loop from scratch
  • How to think about the ethical implications of deep learning and its implementation

Part 2: deep learning from the foundations

Part 2 of the deep learning course shows how to build a state of the art deep learning model from scratch. It covers many topics from the foundations of implementing matrix multiplication and back-propagation, through to high performance mixed-precision training, and the latest neural network architectures and learning techniques.

Applied data ethics

This course focusses on ethics issues that are both urgent and practical. It covers the following topics:

  1. Disinformation
  2. Bias & fairness
  3. Ethical foundations & practical tools
  4. Privacy and surveillance
  5. How did we get here? Our ecosystem
  6. Algorithmic colonialism, and next steps

Computational linear algebra

In this course you can learn how to do matrix computations with acceptable speed and acceptable accuracy.

Code-first introduction to natural language processing

This 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). It also addresses urgent ethical issues, such as bias and disinformation.

In addition to the courses, fast.ai also released four libraries:
fastai v2
fastcore
fastscript
fastgpu

About fast.ai

fast.ai is a self-funded research, software development, and teaching lab, focused on making deep learning more accessible. It was founded by Jeremy Howard and Rachel Thomas in 2016, with Sylvain Gugger completing the core team. They provide free courses, software libraries and research papers (with no ads), and pay all of the costs out of their own pockets. Jeremy and Sylvain have recently published a book entitled: “Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD”.




Lucy Smith , Managing Editor for AIhub.
Lucy Smith , Managing Editor for AIhub.




            AIhub is supported by:


Related posts :



Your right to be forgotten in the age of AI

New models, like ChatGPT, are being trained in ways that make it hard to forget users’ data, raising significant concerns for our privacy online.
22 September 2023, by

Machine learning can level the playing field against match fixing – helping regulators spot cheating

A machine learning model for detecting questionable behaviour and unusual outcomes in basketball games.
21 September 2023, by

The Good Robot Podcast: featuring Meredith Broussard

In this episode, Eleanor and Kerry talk to Meredith Broussard about why sexism, racism and ableism in tech is "More than a Glitch".
20 September 2023, by

Exploring layers in deep learning models: interview with Mara Graziani

Mara tells us about uncovering unique concept vectors through latent space decomposition.
19 September 2023, by

AI-narrated audiobooks are here – and they raise some serious ethical questions

What does this new technology mean for the industry, and for human actors?
18 September 2023, by

Training diffusion models with reinforcement learning

We show how diffusion models can be trained on downstream objectives directly using reinforcement learning.
15 September 2023, by





©2021 - Association for the Understanding of Artificial Intelligence


 












©2021 - ROBOTS Association