20 Sep 2022
Branching out from !learning/computer-science for a more AI-focused learning path.
Not sure if I need to split into AI categories, ie NLP, machine learning, etc..? 🤔
Lists of AI courses
Of interest could be:
CS50 - Introduction to Artificial Intelligence with Python (and Machine Learning), Harvard OCW CS 188 - Introduction to Artificial Intelligence, UC Berkeley - Spring 2015 6.034 Artificial Intelligence, MIT OCW CS221: Artificial Intelligence: Principles and Techniques - Autumn 2019 - Stanford University 15-780 - Graduate Artificial Intelligence, Spring 14, CMU CSE 592 Applications of Artificial Intelligence, Winter 2003 - University of Washington CS322 - Introduction to Artificial Intelligence, Winter 2012-13 - UBC (YouTube) CS 4804: Introduction to Artificial Intelligence, Fall 2016 CS 5804: Introduction to Artificial Intelligence, Spring 2015 Artificial Intelligence - IIT Kharagpur Artificial Intelligence - IIT Madras Artificial Intelligence(Prof.P.Dasgupta) - IIT Kharagpur MOOC - Intro to Artificial Intelligence - Udacity MOOC - Artificial Intelligence for Robotics - Udacity Graduate Course in Artificial Intelligence, Autumn 2012 - University of Washington Agent-Based Systems 2015/16- University of Edinburgh Informatics 2D - Reasoning and Agents 2014/15- University of Edinburgh Artificial Intelligence - Hochschule Ravensburg-Weingarten Deductive Databases and Knowledge-Based Systems - Technische Universität Braunschweig, Germany Artificial Intelligence: Knowledge Representation and Reasoning - IIT Madras Semantic Web Technologies by Dr. Harald Sack - HPI Knowledge Engineering with Semantic Web Technologies by Dr. Harald Sack - HPI T81-558: Applications of Deep Neural Networks by Jeff Heaton, 2022, Washington University in St. Louis
Introduction to Machine Learning MOOC Machine Learning Andrew Ng - Coursera/Stanford (Notes) Introduction to Machine Learning for Coders MOOC - Statistical Learning, Stanford University Foundations of Machine Learning Boot Camp, Berkeley Simons Institute CS155 - Machine Learning & Data Mining, 2017 - Caltech (Notes) (2016) CS 156 - Learning from Data, Caltech 10-601 - Introduction to Machine Learning (MS) - Tom Mitchell - 2015, CMU (YouTube) 10-601 Machine Learning | CMU | Fall 2017 10-701 - Introduction to Machine Learning (PhD) - Tom Mitchell, Spring 2011, CMU (Fall 2014) (Spring 2015 by Alex Smola) 10 - 301/601 - Introduction to Machine Learning - Spring 2020 - CMU CMS 165 Foundations of Machine Learning and Statistical Inference - 2020 - Caltech Microsoft Research - Machine Learning Course CS 446 - Machine Learning, Spring 2019, UIUC (Fall 2016 Lectures) undergraduate machine learning at UBC 2012, Nando de Freitas CS 229 - Machine Learning - Stanford University (Autumn 2018) CS 189/289A Introduction to Machine Learning, Prof Jonathan Shewchuk - UCBerkeley CPSC 340: Machine Learning and Data Mining (2018) - UBC CS4780/5780 Machine Learning, Fall 2013 - Cornell University CS4780/5780 Machine Learning, Fall 2018 - Cornell University (Youtube) CSE474/574 Introduction to Machine Learning - SUNY University at Buffalo CS 5350/6350 - Machine Learning, Fall 2016, University of Utah ECE 5984 Introduction to Machine Learning, Spring 2015 - Virginia Tech CSx824/ECEx242 Machine Learning, Bert Huang, Fall 2015 - Virginia Tech STA 4273H - Large Scale Machine Learning, Winter 2015 - University of Toronto CS 485/685 Machine Learning, Shai Ben-David, University of Waterloo STAT 441/841 Classification Winter 2017 , Waterloo 10-605 - Machine Learning with Large Datasets, Fall 2016 - CMU Information Theory, Pattern Recognition, and Neural Networks - University of Cambridge Python and machine learning - Stanford Crowd Course Initiative MOOC - Machine Learning Part 1a - Udacity/Georgia Tech (Part 1b Part 2 Part 3) Machine Learning and Pattern Recognition 2015/16- University of Edinburgh Introductory Applied Machine Learning 2015/16- University of Edinburgh Pattern Recognition Class (2012)- Universität Heidelberg Introduction to Machine Learning and Pattern Recognition - CBCSL OSU Introduction to Machine Learning - IIT Kharagpur Introduction to Machine Learning - IIT Madras Pattern Recognition - IISC Bangalore Pattern Recognition and Application - IIT Kharagpur Pattern Recognition - IIT Madras Machine Learning Summer School 2013 - Max Planck Institute for Intelligent Systems Tübingen Machine Learning - Professor Kogan (Spring 2016) - Rutgers CS273a: Introduction to Machine Learning (YouTube) Machine Learning Crash Course 2015 COM4509/COM6509 Machine Learning and Adaptive Intelligence 2015-16 10715 Advanced Introduction to Machine Learning Introduction to Machine Learning - Spring 2018 - ETH Zurich Machine Learning - Pedro Domingos- University of Washington Advanced Machine Learning - 2019 - ETH Zürich Machine Learning (COMP09012) Probabilistic Machine Learning 2020 - University of Tübingen Statistical Machine Learning 2020 - Ulrike von Luxburg - University of Tübingen COMS W4995 - Applied Machine Learning - Spring 2020 - Columbia University Machine Learning for Engineers 2022 (YouTube) 10-418 / 10-618 (Fall 2019) Machine Learning for Structured Data
Natural Language Processing
CS 224N - Deep Learning for Natural Language Processing, Stanford University (Lectures - Youtube) CS 224N - Natural Language Processing, Stanford University (Lecture videos) CS 124 - From Languages to Information - Stanford University MOOC - Natural Language Processing, Dan Jurafsky & Chris Manning - Coursera fast Code-First Intro to Natural Language Processing (Github) MOOC - Natural Language Processing - Coursera, University of Michigan CS224U: Natural Language Understanding - Spring 2019 - Stanford University Deep Learning for Natural Language Processing, 2017 - Oxford University Accelerated Natural Language Processing 2015/16- University of Edinburgh Natural Language Processing - IIT Bombay CMU Advanced NLP 2021 CMU Neural Nets for NLP 2021 Natural Language Processing - Michael Collins - Columbia University CMU CS11-737 - Multilingual Natural Language Processing UMass CS685: Advanced Natural Language Processing (Spring 2022) Natural Language Processing (CMSC 470)
Course is comprised of short videos covering:
Machine Learning What is data The terminology of AI What makes an AI company? What Machine Learning can and cannot do Intuitive explanation of deep learning Workflow of a Machine Learning project Workflow of a Data Science project Every job function needs to learn to use data How to choose an AI project Working with an AI team Technical tools for AI teams Case study: Smart speaker Case study: Self-driving car Example roles of an AI team AI Transformation Playbook AI pitfalls to avoid Taking your first step in AI Survey of major AI applications Survey of major AI techniques A realistic view of AI Discrimination / Bias Adversarial attacks Adverse uses AI and developing nations AI and jobs
Good start for a lot of people, too high-level for me at this stage.
Harvard's CS50’s Introduction to Artificial Intelligence with Python
➤ highly recommend
➤ highly recommend
other videos from Lex Fridman:
1) Introduction to machine learning
- get started with ML
- Learn about supervised ML
2) machine learning crash course
- How ML differs from traditional programming
- How does gradient descent work?
- End-to-end ML engineering
- Production ML systems and more..
3) Introduction to ML problem framing
- Understand how to frame the ML problem
4) Data preparation and FE in ML
- Data preparation
- Data transformation
- Feature engineering
5) testing and debugging ML models
- Train and test ML models
- Debugging the ML models
I am really enjoying @karpathy's youtube series (https://t.co/qONDNqLiGk) on machine learning:— MartinK (@mdkO_o) November 8, 2022
- it picks you up were you are at, if you have a dev background
- starts with the basics
- while still being relevant, due to using pytorchs api
Genius! I cannot recommend it enough.
a series of videos on Youtube - "It's absolutely the best introduction to neural networks I have seen." @krzysztofwos on Twitter.
26 Oct 2022
Learning AI is a bit overwhelming 😅
I have done several courses like:
- Andrew Ng's "AI for everyone" on deeplearning listed above (too shallow/high level)
- Lex Fridman's "Deep Learning Basics" MIT course introduction (insightful, but too deep for me)
- Jose Portilla' "Practical AI with Python and Reinforcement Learning" on Udemy (good to get a sense at Python level, but too low level at this point for me)
- skimmed through some Harvard courses listed above (same outcome as with Lex Fridman) and read many blog posts, etc..
I have experience with Python (for automation mainly) and have played with Stable Diffusion via CLI and other models via online interfaces.
I feel that I'm missing education in between - mid level :)
examples of missing connections in my mind at this stage:
- what are all the different AI fields and how do they interact all together? eg are computer vision and NLP different fields with no AI overlap but leveraging the same methods (supervised/unsupervised/deep) and tools (Tensorflow, etc..)?
- what defines an AI model? algorithm? eg is it only about changing the training set and weight parameters for specific criteria/neurons?
- how does it look like? Just a Python library? With or without dataset included?
- with deep learning, is it just running each time an input from a given dataset, ie train and ouput in same run, or does a computed algorithm get generated off the training dataset?
- what are the different kinds of tools required to create an AI model? And to implement AI? And how do they interact?
- what are the different kind of AI platforms and what do they do? Only providing GPUs in the cloud and a library of models/datasets? eg what is the difference between huggingface.co and c3.ai? Same thing but for consumers (ie developers) and enterprises?
- how do you use an existing model in production (ie for real-life usages)? Via API?
- how do you feedback results to an AI model for it to learn further?
- my brain hurts from the complexity, will an AGI also experience brainaches? :)
What would be the resources to best advance my learning at this stage?
If helpful for guidance, my main practical interest/use of AI is for Sales/business (so probably focus on NLP?), though my curiosity is wider :)