Neural Networks and Deep Learning Reviews and details

Social recommendations and mentions

• How do I begin building AI tools for myself?

  For neural network theory, I'm very fond of http://neuralnetworksanddeeplearning.com, but you'll need calculus and some linear algebra to understand it. Source: 5 months ago

• What would be a project oriented roadmap to learn ML, deep learning (assuming I know Python and the required math - calculus, linear algebra and stats)?

  Alternatively, building them from scratch in numpy is definitely possible and an excellent way to learn the fundamentals. It will take some time though (debugging issues with a hand-rolled LSTM is very, very painful). There's a zillion tutorials/books out there (I think I started with http://neuralnetworksanddeeplearning.com). Source: 5 months ago

• Ask HN: In 2023 which is the best path to learn machine and deep learning?

  - http://neuralnetworksanddeeplearning.com/ The Watch the Caltech telecourse. - Source: Hacker News / 8 months ago

• Ask HN: What books or courses do you know similar to "From Nand to Tetris"?

  Neural Networks and Deep Learning, a free online book. http://neuralnetworksanddeeplearning.com/. - Source: Hacker News / 9 months ago

• Why Do ML on the Erlang VM?

  Many years ago I was studying deep learning using this resource: * http://neuralnetworksanddeeplearning.com/ I decided to try to implement everything from scratch in Elixir (after initially doing all the math with pen and paper on a trivial example to get the feel of it). Obviously pure elixir was extremely slow, so I started creating NIFs to pass over matrix multiplication to OpenBLAS. Then I was thinking more... - Source: Hacker News / 11 months ago

• Please don't make fun of me.

  This book is free and has a great section on backpropagation, which is how neural networks adjust their weights, including the math. The code snippets are in python 2 though so just be careful when copying and pasting. Http://neuralnetworksanddeeplearning.com/. Source: 11 months ago

• How do I transition from Junior DevOps to ML Engineer/Researcher?

  Current idea:-solve this books exercises, write it up in Latex, put it on githttp://neuralnetworksanddeeplearning.com-tidy up my ML/DL university assignments and put them on Git-after that, road to Kaggle Master/Grandmaster?-do a full ML+MLOps personal project and put it on Git/online. Source: 12 months ago

• Would upskilling with a graduate certificate in bioinformatics help land a Job in USA or Europe?

  For AI, I personally recommend http://neuralnetworksanddeeplearning.com/ and the courses on https://www.fast.ai/. Source: 12 months ago

• The End of the Beginning (2020)

  ChatGPT feels like a good example, I think 6 months ago that those who weren't in the know would be able to predict something like that. I know I wouldn't be able to, and I even build some small neural nets for fun and read Neural Networks and Deep Learning [1]. I am by no means an expert in the field, but I know some basics and have programmed in all kinds of languages, watched 2 Minute Papers quite a bit and yet... - Source: Hacker News / about 1 year ago

• am I too inexperienced to start learning?

  Neural networks and deep learning Http://neuralnetworksanddeeplearning.com/. Source: about 1 year ago

• Math foundations and practical side of ML and DL for math research

  Gilbert Strang wrote a book called “Linear Algebra and Learning From Data” that’s available for free download, I would highly recommend that. I’ll also recommend the free online “book” by Michael Nielsen, found at http://neuralnetworksanddeeplearning.com. Source: about 1 year ago

• Ask HN: In 2023, what resource will you pick for learning AI/ML/DL?

  An online book by Michael Nielsen : http://neuralnetworksanddeeplearning.com/ It starts from basics and builds a CNN to recognize handwritten digits. I found it very helpful during my start of the journey. - Source: Hacker News / over 1 year ago

• Ask HN: What are the foundational texts for learning about AI/ML/NN?

  Http://neuralnetworksanddeeplearning.com (full text) The first chapter walks through a neural network that recognizes handwritten digits implemented in a little over 70 lines of Python and leaves you with a very satisfying basic understanding of how neural networks operate and how they are trained. - Source: Hacker News / over 1 year ago

• Ask HN: Tutorials Written with Heavy Dependencies

  Machine learning is an enormous field, and if you are after a explanation/exploration from the ground up, then Kevin Murphy's Probabilistic Machine Learning: An Introduction is very good, but a bit of a tome. If instead, you want to focus on neural networks, I found Michael Nielsen's Neural Networks and Deep Learning, available at http://neuralnetworksanddeeplearning.com/, an excellent resource for implementing... - Source: Hacker News / over 1 year ago

• Learning machine learning

  You could have a look at http://neuralnetworksanddeeplearning.com. Back in the day, I built a basic neural network from scratch (with plain NumPy) and trained it using backpropagation following this book/site. Surprisingly, I was able to make it recognize my own handwriting (using MNIST was too boring). It was a basic feedforward neural network, though, not a convolutional one or anything fancy that's specifically... Source: over 1 year ago

• Noob question: (weight * input) + bias

  This book has some good explanations on these concepts Http://neuralnetworksanddeeplearning.com. Source: over 1 year ago

• Ask HN: How to become a deep learning 'master' in 2022?

  This is the best starting point: http://neuralnetworksanddeeplearning.com/ Then: https://m.youtube.com/playlist?list=PL5-TkQAfAZFbzxjBHtzdVCWE0Zbhomg7r and/or: https://www.fast.ai/posts/2022-07-21-dl-coders-22.html. - Source: Hacker News / over 1 year ago

• Where to go from the Neural Network Series

  I read now the excellent book recommended by 3b1b It’s available for free here and you can donate if you find it useful. Source: over 1 year ago

• Learn deep neural networks and autoencoder an Python

  It doesn't cover autoencoders, but this is a nice easy intro to deep learning. Source: almost 2 years ago

• What is the difference between a ‘parameter’ and a ‘neuron’ (aka ‘perceptron’) for modern neural nets like GPT-3?

  I think you definitely may want to read this: http://neuralnetworksanddeeplearning.com/ the first chapters may enlighten you on the basics. Source: almost 2 years ago

• ML without a framework.

  If you are keen on getting your hands a little dirty, I'd recommend you read and code-along with http://neuralnetworksanddeeplearning.com/. Source: about 2 years ago