How Neural Networks Learn Part II - Search Videos

Gradient descent, how neural networks learn | Deep learning, part 2 on Make a GIF

Gradient descent, how neural networks learn | Deep learning, part 2 on Make a GIF

Friday's MIT lecture covered what neural networks are. Tonight's Part 2 shows you every way training can break, in one image every ML engineer learns the hard way.Spending my sunday evening with this one. Bookmark & watch with me, no matter what, best way to close the weekend.

Friday's MIT lecture covered what neural networks are. Tonight's Part 2 shows you every way training can break, in one image every ML engineer learns the hard way.Spending my sunday evening with this one. Bookmark & watch with me, no matter what, best way to close the weekend.

11.1K views2 months ago

5.1.2 Backpropagation Algorithm by Andrew Ng

5.1.2 Backpropagation Algorithm by Andrew Ng

12.1K viewsMay 15, 2019

YouTubeComputer Science Engineering

Lecture - 27 Learning : Neural Networks

Lecture - 27 Learning : Neural Networks

125.7K viewsApr 30, 2008

YouTubenptelhrd

5.1.3 Backpropagation Intuition by Andrew Ng

5.1.3 Backpropagation Intuition by Andrew Ng

2.9K viewsMay 15, 2019

YouTubeComputer Science Engineering

Convolutional Neural Network (CNN) in Deep Learning - GeeksforGeeks

Convolutional Neural Network (CNN) in Deep Learning - GeeksforGeeks

geeksforgeeks.org

How neural networks work

How neural networks work

Khan AcademyCode.org

Neural Networks and Deep Learning: A Textbook | Guide books | ACM Digital Library

MIT teaches one neural network class. The engineers who took it ended up running model training at OpenAI, Anthropic, and DeepMind.The 2026 edition is out. Lecture 1 is by Alexander Amini. His startup, Liquid AI, just hit a 2.3 billion dollar valuation while he was preparing the slides.If you can't build a neural network from scratch in 2026, you don't get to call yourself an AI engineer.

1.3K views1 month ago

Computing Graph Neural Networks: A Survey from Algorithms to Accelerators | ACM Computing Surveys

Triton: an intermediate language and compiler for tiled neural network computations | Proceedings of the 3rd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages

Neural networks might speak English, but they think in shapes.Understanding their rich *neural geometry* is key to understanding how they work – and to debugging and controlling them with precision.Starting today, we’re releasing a series of posts on this research agenda. 🧵

3.2M views1 month ago

Google has unveiled new research that could signal the end of the Transformer era, introducing a breakthrough in RNN architecture.For years, models like ChatGPT and Gemini have relied on Transformers, which suffer from “quadratic complexity” a bottleneck where compute costs skyrocket as prompts get longer, because the model must process every word against every other word.Recurrent Neural Networks (RNNs) are significantly faster and cheaper, but they traditionally suffer from “amnesia” due to a

389 views2 weeks ago

Improved Recurrent Neural Networks for Session-based Recommendations | Proceedings of the 1st Workshop on Deep Learning for Recommender Systems

Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks | Proceedings of the 19th ACM International Conference on Multimodal Interaction

What if Your Neural Network Was Forced to Obey Physics?Physics-Informed Neural Networks (PINNs) are neural networks trained to satisfy a differential equation by building the PDE residual directly into the loss. They emerged from a very practical problem...classical PDE pipelines can be brilliant, but they often demand heavy discretization work (meshes, stencils, stability tuning), and the method you build is usually tied to one geometry and one solver setup. A PINN flips the workflow by represe

17.2K views1 month ago

x.comMathelirium

It’s all already happening tho that’s the funny part and the framing is absolute. Only they aren’t using lab grown cells. They have collected your biometric data through the TOS of their apps as well as the field your heart produces and the nano particulates in the the air which can; map your neural network, remotely manipulate your nervous system, speak into your mind (V2K), induce schizophrenia (Havana syndrome) etc. This has been going on for decades bro where have you been?

3K views1 month ago

x.com🜌🜈🜓

See more