Machine Learning:
Machine learning is the development of algorithms and systems that can learn from data and make predictions or decisions. Machine learning is a subset of artificial intelligence that focuses on creating machines that can perform tasks that normally require human intelligence. Machine learning can be divided into different types, such as supervised learning, unsupervised learning, reinforcement learning, and deep learning.
1. Stanford Machine Learning CS 229/ Full Course by Andrew Ng/ This course provides a broad introduction to machine learning and statistical pattern recognition. It has 20 videos each 1 hour and 20 minutes: https://www.youtube.com/playlist?list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU
2. Statistical Machine Learning/ All lectures of the course “Statistical Machine Learning” by Ulrike von Luxburg, University of Tübingen, Summer Term 2020./ It consists of 58 videos from 10 minutes to around an hour./ https://www.youtube.com/playlist?list=PL05umP7R6ij2XCvrRzLokX6EoHWaGA2cC
3. Cornell Applied Machine Learning CS 5787/ Volodymyr Kuleshov/ Lecture videos and materials from the Applied Machine Learning course at Cornell Tech, taught in Fall 2020. It has 80 videos from 8 minutes to 30 minutes each:https://www.youtube.com/playlist?list=PL2UML_KCiC0UlY7iCQDSiGDMovaupqc83
4. Neural Networks: Zero to Hero/ Andrej Karpathy (2022 and 2023): 8 videos from 40 minutes to 2 hours and 30 minutes: https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ
5. Introduction to Machine Learning/ Tübingen Machine Learning Lectures for the course “Introduction to Machine Learning” (Machine Learning I) by Dmitry Kobak, University of Tübingen, Winter Term 2020/21. / The course serves as a basic introduction to machine learning and covers key concepts in regression, classification, optimization, regularization, clustering, and dimensionality reduction. The course is aimed at master students in neuroscience and other sciences. The course assumes basic familiarity with calculus, probability theory, and linear algebra (matrices). 11 videos from 37 minutes to 1 hour 20 minutes: https://www.youtube.com/playlist?list=PL05umP7R6ij35ShKLDqccJSDntugY4FQT
6. Making Friends with Machine Learning/ Google Cloud by Cassie Kozyrkov/ 126 videos some a couple of minutes and some 2 hours!/ https://www.youtube.com/playlist?list=PLRKtJ4IpxJpDxl0NTvNYQWKCYzHNuy2xG
7. Machine Learning Engineering for Production (MLOps)/ This course by Andrew Ng’s DeeplearningAI has 40 videos from a few minutes to 15 minutes each: https://www.youtube.com/playlist?list=PLkDaE6sCZn6GMoA0wbpJLi3t34Gd8l0aK
Deep Learning
Deep learning is a type of machine learning that uses neural networks to learn from large amounts of data and perform complex tasks. Neural networks are composed of layers of nodes that can process information and learn from their inputs and outputs. Deep learning is a subset of machine learning that can achieve state-of-the-art results on challenging problems such as image recognition, natural language processing, and speech recognition.
1. Stanford Deep Learning CS 230 Autumn 2018/ Graduate course taught by Andrew Ng/ You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, Adversairal attacks, BatchNorm, Xavier/He initialization, and more/ 10 Videos from 40 minutes to 90 minutes: https://www.youtube.com/playlist?list=PLoROMvodv4rOABXSygHTsbvUz4G_YQhOb
2. Introduction to Deep Learning (MIT)/ This is the graduate course of MIT 6.S191: Introduction to Deep Learning from 2018 to 2023, and some of the topics are repeated by different lecturers. Most of the 63 videos are around 40 minutes to an hour: https://www.youtube.com/playlist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI
3. Deep Unsupervised Learning/ Berkeley Spring 2020 by Pieter Abbeel and his colleagues. Peter is a professor of electrical engineering and computer sciences, Director of the Berkeley Robot Learning Lab, and co-director of the Berkeley AI Research Lab at the University of California, Berkeley/ The course is 12 long videos mostly around 2 hours each: https://www.youtube.com/playlist?list=PLwRJQ4m4UJjPiJP3691u-qWwPGVKzSlNP
4. MIT: Deep Learning for Art, Aesthetics, and Creativity/ MIT 6.S192: Deep Learning for Art, Aesthetics, and Creativity/ 22 videos mostly around an hour, a couple of them close to two hours. The courses are pre-Gen-AI/DALLE-era so you can feel how AI pace is moving fast: https://www.youtube.com/playlist?list=PLCpMvp7ftsnIbNwRnQJbDNRqO6qiN3EyH
5. NYU Deep Learning SP21, Alfredo Canziani/ This course has 33 longer videos isially over one hour each: https://www.youtube.com/playlist?list=PLLHTzKZzVU9e6xUfG10TkTWApKSZCzuBI
6. Practical Deep Learning for Coders / This course by Jeremy Howard consists of 8 videos from 1 hour 16 minutes to 1 hour 40 minutes. This free course is designed for people with some coding experience who want to learn how to apply deep learning and machine learning to practical problems: https://www.youtube.com/playlist?list=PLfYUBJiXbdtSvpQjSnJJ_PmDQB_VyT5iU
Natural Language Processing (NLP)
NLP stands for natural language processing, which is the branch of AI that deals with understanding and generating natural language, such as text and speech. NLP enables computers to communicate with humans in natural ways, such as answering questions, translating languages, summarizing texts, and writing essays. NLP is a very broad and diverse field that covers many subfields, such as syntax, semantics, pragmatics, discourse, sentiment analysis, dialogue systems, information extraction, and natural language generation.
1. Stanford’s Natural Language Understanding/ Stanford CS224U / This course consists of 63 videos some as short as a few minutes and a couple of not long videos. This course is focused on developing systems and algorithms for robust machine understanding of human language. It draws on theoretical concepts from linguistics, natural language processing, and machine learning: https://www.youtube.com/playlist?list=PLoROMvodv4rPt5D0zs3YhbWSZA8Q_DyiJ
2. CMU Advanced NLP 2022 by Graham Neubig consists of 24 longer videos over one hour each: https://www.youtube.com/playlist?list=PL8PYTP1V4I8D0UkqW2fEhgLrnlDW9QK7z
3. CMU Multilingual NLP by Graham Neubig consists of 21 longer videos mostly around one hour each: https://www.youtube.com/playlist?list=PL8PYTP1V4I8BhCpzfdKKdd1OnTfLcyZr7
4. Advanced NLP / UMass CS685: Advanced Natural Language Processing (Fall 2020) by Mohit Iyyer has 26 videos around one hour each: https://www.youtube.com/playlist?list=PLWnsVgP6CzadmQX6qevbar3_vDBioWHJL
Computer Vision
Computer vision is a subfield of artificial intelligence that seeks to make computers understand the contents of digital images or videos and make some sense out of them. Computer vision uses techniques such as image processing, feature extraction, object detection, face recognition, and segmentation to enable computers to see and analyze the visual world. Computer vision is an application of machine learning and deep learning that can be used for various purposes such as security, surveillance, entertainment, and education.
1. Deep Learning for Computer Vision with Python and TensorFlow – Complete Course by Freecodecamp.org teaches you the basics of computer vision with deep learning and how to implement the algorithms using Tensorflow. It’s done by Folefac Martins from Neuralearn.ai and the video is around 37 hours long: Deep Learning for Computer Vision with Python and TensorFlow – Complete Course – YouTube
2. Advanced Computer Vision with Python – Full Course by Freecodecamp.org/ In this 6-hour video you will learn state of the art computer vision techniques by building five projects with libraries such as OpenCV and Mediapipe. The course is taught by Murtaza Hassan (murtazahassan.com) Advanced Computer Vision with Python – Full Course – YouTube
3. Deep Learning for Computer Vision / This course by Michigan Online covers learning algorithms, neural network architectures, and practical engineering tricks for training and fine-tuning networks for visual recognition tasks. It has 22 videos over 1 hour each. It doesn’t require background in computer vision and it strats from general topics: https://www.youtube.com/playlist?list=PL5-TkQAfAZFbzxjBHtzdVCWE0Zbhomg7r
Reinforcement Learning
Reinforcement learning is a type of machine learning that teaches agents to learn from their own actions and rewards in an environment. Reinforcement learning enables computers to learn complex behaviors and skills without explicit supervision or labels, such as playing games, controlling robots, and optimizing systems. Reinforcement learning is a very challenging and active field that covers many subfields, such as value-based methods, policy-based methods, model-based methods, multi-agent systems, and exploration-exploitation trade-off.
Deep Reinforcement Learning https://lnkd.in/e6gyvp4s
19. Stanford: Reinforcement Learning https://lnkd.in/eGR-5THW
Transformers
Transformers are a type of neural network architecture that uses attention mechanisms to capture long-range dependencies and context in sequential data. Transformers have been very successful in NLP tasks, such as machine translation, text summarization, text generation, and question answering. Transformers have also been applied to other domains, such as computer vision, speech recognition, and reinforcement learning. Transformers are a very powerful and flexible architecture that covers many variants, such as BERT, GPT-3, ViT, and DETR.
1. Stanford – Transformers/ Stanford CS25 – Transformers United/ 18 videos mostly around an hour: https://www.youtube.com/playlist?list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM
Books:
Deep Reinforcement Learning in Action: