Understanding Deep Learning by Prof. Simon J.D. Prince is a new book that focuses, as the name implies, on the Foundation of deep learning.
๐งถ๐งต๐๐ผ
(2/4)The book covers topics such as:
โ Foundation of machine learning (supervised and unsupervised learning, lost function, gradients algorithm, etc.)
โ Shallow and deep neural network
โ Convolutional networks
โ Transformers
โ Diffusion models
โ Deep reinforcement learning
(3/4) ๐๐จ๐จ๐ค ๐ฐ๐๐๐ฌ๐ข๐ญ๐: https://udlbook.github.io/udlbook/
Thanks to the author for making this book available for free online! ๐๐ผ
๐๐ญ๐๐ซ๐๐ฎ๐๐ค๐ฌ ๐๐จ๐ฌ๐ญ ๐ข๐ง๐๐๐ฑ (i.e., cost as the number of granda cappuccino caps):
๐๐ฆ๐๐ณ๐จ๐ง: 24 โ๏ธ
๐๐ฎ๐๐ฅ๐ข๐ฌ๐ก๐๐ซ: 26 โ๏ธ
๐๐ง๐ฅ๐ข๐ง๐: 0 โ๏ธ ๐ฆ
Are you planning to learn a new data science or engineering skill as your New Yearโs resolution ? Here is a collection of random open and free courses and resources I came across during the past year covering various topics, including deep learning, NLP, Python, statistics, and more.
(1/2) New book for Deep Learning (draft mode) ๐
The Mathematical Engineering of Deep Learning is a new book by Benoit Liquet, Sarat Moka, and Yoni Nazarathy.
As its name implies, it focuses on the mathematical engineering of #deeplearning and covers topics such as:
โ Foundation of machine learning and deep learning
โ Optimization algorithms
โ Convolutional neural networks
โ Transformers
โ Generative models
โ Diffusion models
A new class of antibiotics discovered using graph #deeplearning#AI
This is extraordinary for combating antibiotic resistance, which has been projected to cause 10 million deaths / year by 2050.
"To figure out how the model was making its predictions, the researchers adapted an algorithm, Monte Carlo tree search, which has been used to help make other deep learning models more explainable."
Are #neuro people interested in trying and using it? Maybe pointing to the best experts to review it even?
Let us know! ๐ง ๐จ๐พโ๐ป๐ฉ๐ผโ๐ป๐งโ๐ป
The rapid AI developments still give me mixed feelings of excitement and disappointment.
Excitement because I'm a graphics and tech lover, disappointment because AI-generated stuff doesn't give me the positive feeling I get when seeing something that was actually crafted by a person.
The same goes for using AI tools myself: I quickly get bored, because there's no challenge. It feels like performing a glorified Google image search, instead of challenging yourself with a creative project, conceiving creation methods, falling, getting up again, and finally getting the satisfaction of something you have carefully crafted with emotional involvement.
Meet #Gemini - the first model to outperform human experts on #MMLU (Massive Multitask Language Understanding), one of the most popular methods to test the performance of language models: https://bit.ly/3ReWtNO
This is brought to you by our Reinforcement Learning homework in which we were asked to implement the SAC algorithm. Something tells me this was not the ideal choice for literally the first Reinforcement Learning assignment given to students. ๐ซ
Machine Learning mit Python โ KI und Deep Learning in 5 Webinaren erklรคrt
Ab dem 11.01. lernen Sie in fรผnf Webinaren, die Welt der kรผnstlichen Intelligenz kennen. Von Machine Learning รผber neuronale Netze bis zu Deep Learning.
I ran a quick Gradient Boosted Trees vs Neural Nets check using scikit-learn's dev branch which makes it more convenient to work with tabular datasets with mixed numerical and categorical features data (e.g. the Adult Census dataset).
Let's start with the GBRT model. It's now possible to reproduce the SOTA number of this dataset in a few lines of code 2 s (CV included) on my laptop.
(1/2) Introduction to the MLX - Apple's array framework for machine learning on Apple silicon โค๏ธโค๏ธโค๏ธ
The Apple Machine Learning Research team released a Python library yesterday to support array processing on Apple silicon machines (e.g., M1, M2, M3). This framework is inspired by similar frameworks like NumPy, PyTorch, Jax, and ArrayFire, levering Apple CPU architecture for optimal performance ๐.
(1/2) ISLR with applications in Python online course! ๐
Any fans of ๐๐ง ๐๐ง๐ญ๐ซ๐จ๐๐ฎ๐๐ญ๐ข๐จ๐ง ๐ญ๐จ ๐๐ญ๐๐ญ๐ข๐ฌ๐ญ๐ข๐๐๐ฅ ๐๐๐๐ซ๐ง๐ข๐ง๐ โค๏ธ? Staford released today the Python online version course for the ISLR book. The course covering topics such as:
โ Regression and classification
โ Linear model selection and regularization
โ Non-linear Regression
โ Tree-based methods
โ Support vector machines
โ Deep learning
โ Unsupervised learning