Visit https://course.fast.ai for code, notebooks, quizzes, etc. This course is for people with some coding experience who want to learn how to apply deep learning and machine learning to real-world problems. There are 9 lessons and each lesson lasts approximately 90 minutes.

We cover topics such as: how to:
– Build and train deep learning, random forest and regression models
– Implement models
– Apply deep learning to computer vision, natural language processing, tabular analysis, and collaborative filtering problems
– Use PyTorch, the world's fastest growing deep learning software, along with popular libraries such as fastai, Hugging Face Transformers and gradio

You don't need any special hardware or software. We'll show you how to use free resources for both building and deploying models. You don't need university mathematics either; during the course we will teach you the calculus and linear algebra you need.

00:00 – Introduction
00:25 – What has changed since 2015
01:20 – It's a bird
02:09 – Pictures are made of numbers
03:29 – Download images
04:25 – Create a DataBlock and student
05:18 – Train the model and make a prediction
07:20 – What can deep learning do now?
10:33 – Pathways Language Model (PaLM)
15:40 – How the course is taught. Top-down learning
19:25 – Jeremy Howard's qualifications
22:38 – Comparison between modern deep learning and 2012 machine learning practices
24:31 – Visualization of layers of a trained neural network
27:40 – Image classification applied to audio
28:08 – Image classification applied to time series and fraud
30:16 – Pytorch vs. Tensorflow
31:43 – Example of how Fastai builds on Pytorch (AdamW optimization)
35:18 – Using Cloud Servers to Run Your Notebooks (Kaggle)
38:45 – Bird or no bird? & explanation of some Kaggle features
40:15 – How to import libraries like Fastai into Python
40:42 – Best practice – viewing your data between steps
42:00 – Datablocks API umbrella explanation
44:40 – Explanation of Datablocks API parameters
48:40 – Where to find fastai documentation
49:54 – Fastai's student (combines model and data)
50:40 – Fastai's available pre-trained models
52:02 – What is a pre-trained model?
53:48 – Testing your model with the prediction method
55:08 – Other applications of computer vision. Segmentation
56:48 – Explanation of the segmentation code
58:32 – Tabular analysis with fastai
59:42 – explanation of show_batch method
1:01:25 – Example of collaborative filtering (recommendation system).
1:05:08 – How to Turn Your Notebooks into a Presentation Tool (RISE)
1:05:45 – What else can you make with notebooks?
1:08:06 – What can deep learning do right now?
1:10:33 – The first neural network – Mark I Perceptron (1957)
1:12:38 – High level machine learning models
1:18:27 – Homework

Thanks to bencoman, mike.moloch, amr.malik and gagan at forums.fast.ai for doing the transcription.

Thanks to Raymond-Wu at forums.fast.ai for help with chapter titles.

Please take the opportunity to connect and share this video with your friends and family if you find it helpful.