Autoencoder by hand✍️Excel~ I designed this exercise to show... how an Encoder-Decoder network convert input to code and reconstruct input from code. It is annotated with equations, PyTorch, and graphs. 👇Join the 'AI Math' community. Download xlsx.show more

Transformer by hand✍️ Excel ~ I designed this exercise... to show the core math of a Transformer model is to combine columns (attention), combine rows (feed forward), and repeat.👇Join the 'AI Math' community. 👇Download xlsx.show more

ResNet by hand✍️Excel~ I designed this exercise to compare... a ResNet to an MLP and show skip-connections are simply identity matrices next to weights and biases. I also made a medium version to show how it scales. 👇Join the 'AI Math' community. Download xlsx.show more

AlphaFold by hand✍️ Excel ~ I designed this exercise... to show (1) MSA multi-head attention, (2) Pair triangular update, two key components of the EvoFormer architecture.👇Join the AI Math community. Download xlsx.show more

Backpropagation by hand✍️ ~ spreadsheet. I designed this exercise... to show it is possible to calculate backpropagation for a non-trivial, three-layer network by hand. p.s. I just started this community to share useful resources on AI math. 👇 Join the community.show more

Transformer: Multi-Head Attention ~ Math vs Code 🔢💻 ~... I made this visualization to show you how to implement the multi-head attention math in PyTorch within 50 LoC. Multi-Head Attention is what makes the Transformer's performance outstanding. It captures and represents more diverse linguistic relationships and patterns, and attends to different learned input embedding spaces. The parallel computing design also makes the model more efficient.show more

[VAE] by Hand ✍️ A Variational Auto Encoder (VAE)... learns the structure (mean and variance) of hidden features and generates new data from the learned structure. In contrast, GANs only learn to generate new data to fool a discriminator; they may not necessarily know the underlying structure of the data. The International Conference on Learning Representations (ICLR) this year announced its first ever "Test of Time Award" to recognizes the VAE paper, published 10 years ago. This exercise demonstrates how to calculate a VAE by hand. [1] Given: ↳ Three training examples X1, X2, X3 ↳ Copy training examples to the bottom ↳ The purpose is to train the network to reconstruct the training examples. ↳ Since each target is a training example itself, we use the Greek word "auto" which means "self." This crucial step is what makes an autoencoder "auto." [2] Encoder: Layer 1 + ReLU ↳ Multiply inputs with weights and biases ↳ Apply ReLU, crossing out negative values (-1 -> 0) [3] Encoder: Mean and Variance ↳ Multiply features with two sets of weights and biases ↳ 🟩 The first set predicts the means (𝜇) of latent distributions ↳ 🟪 The second set predicts the standard deviation (𝜎) of latent distributions [4] Reparameterization Trick: Random Offset ↳ Sample epsilon ε from the normal distribution with mean = 0 and variance = 1. ↳ The purpose is to randomly pick a offset away from the mean. ↳ Multiply the standard deviation values with epsilon values. ↳ The purpose is to scale the offset by the standard deviation. [5] Reparameterization Trick: Mean + Offset ↳ Add the sampled offset to predicted mean ↳ The result are new parameters or features 🟨 as inputs to the Decoder. [6] Decoder: Layer 1 + ReLU ↳ Multiply input features with weights and biases ↳ Apply ReLU, crossing out negative values. Here, -4 is crossed out. [7] Decoder: Layer 2 ↳ Multiply features with weights and biases ↳ The output is Decoder's attempt to reconstruct the input data X from reparameterized distributions described by 𝜇 and 𝜎. [8]-[10] KL Divergence Loss [8] Loss Gradient: Mean 𝜇 ↳ We want 𝜇 to approach 0. ↳ A lot of math called SGVB simplifies the calculation of loss gradients to simply 𝜇 [9,10] Loss Gradient: Stdev 𝜎 ↳ We want 𝜎 to approach 1. ↳ A lot of math simplifies the calculation to 𝜎 - (1/ 𝜎) [11] Reconstruction Loss ↳ We want the reconstructed data Y (dark 🟧) to be the same as the input data X. ↳ Some math involving Mean Square Error simplifies the calculation to Y - X.show more

MLP in PyTorch by hand ✍️ ~ 7 steps... walkthrough below Goal: fill in every blank in the PyTorch code to build a multi-layer perceptron. 1. Given Let us start with a code template on the left and the network it is supposed to build on the right. Every blank in the code can be worked out from the picture. 2. Linear layer We count: 3 features in, 4 features out. So the weight matrix is 4 by 3. There is an extra column for the biases, which means bias = T. 3. ReLU Let us apply the activation. ReLU crosses out the negatives, so -1 becomes 0. 4. Linear layer The input size is 4, because that is what the previous layer put out. The output size is 2. A 2 by 4 weight matrix, and this time no extra column, so bias = F. 5. ReLU We cross out the negatives again. 6. Linear layer Two features in, five out. A 5 by 2 weight matrix, with a bias column, so bias = T. 7. Sigmoid Let us finish. Sigmoid squashes the raw scores (3, 0, -2, 5, -5) into probabilities between 0 and 1. You have just implemented a three-layer deep neural network by hand. ✍️ == Story == Three years ago I gave this exercise to my students, to connect the code to the math. They found it odd. Every other AI course they were taking lived inside a Jupyter notebook, and here I was handing out paper. Three years later, my colleagues are the ones rushing to move their materials to paper. The exercise has not changed. Paper still asks the one thing a notebook lets you skip: do you actually understand what the code is doing? If you can tell me why the weight matrix is 4 by 3, and why bias is F on the second layer, you understand nn.Linear better than someone who has been copy-pasting it for a year. 💾 Save this post! #AIbyHand #PyTorch #DeepLearningshow more

Who said range sliders need to be straight and... boring?! Hey CSS, distort the line! 〰️ Another funny demo powered by border-shape, scroll-driven animations, and more The HTML code? Only an input element (no extra code is needed)show more

understand AI like this: if your input is dumb,... your output will be dumb, and if your input is creative, your output will be creative. this is it. so, you need to provide about 70% of the context from your own brain to the ai to get the best outputs.show more

Training Wan 2.1-1.3B to use Qwen3-VL-2B text encoder. Doing... 33% text only, 33% VL only, and 33% both. Just pretraining the two text input linear layers for now. It is amazing how quickly a model can adapt to a different text encoder. This is 25,750 steps, BS of 10.show more

A FLY IS NOW WRITING PYTHON CODE WITH ITS... OWN NERVOUS SYSTEM I genuinely didn't expect a fly to end up behind a code editor. The setup is strangely simple. A fly sits on a keyboard while its neural activity is captured in real time. On the other side of the screen, Python code starts appearing line by line inside wordle_solver_v1.py, with the neural visualization changing as the input comes through. The model contains 100,010 flyemg neurons, with 88,172 represented in the current neural model. As activity changes, the system translates those signals into keyboard input and the cursor keeps moving through the code. Then you start looking at what is actually being typed. import random import unicodedata def quitar_acentos(palabra): It's not just random characters filling the editor. The video shows an actual Python function being constructed while the neural activity and keyboard input remain synchronized beside it. Brain activity → keyboard → code. A tiny biological nervous system is being used as the interface between a fly and a programming environment. The fly isn't sitting there watching someone code. It's sitting on the keyboard while the system turns its neural activity into the next input. And somehow the first thing it ended up building was a Wordle solvershow more

At MIT, I learned about RNNs in my NLP... class with Prof. Michael Collins. He built a model from my keystrokes to predict who I was. To me, it felt like a magic box. Years later, when I had to teach RNNs, I forced myself to go inside the box. ⬇️ Download: First, with a tiny example on paper by hand ✍️. Then, a slightly larger one in Excel. That’s when it finally clicked: 👉 The weights are reused (weight matrices on the left side) 👉 The hidden states are passed down (H's) When I built it by hand and saw everything visually, it clicked, just math you can actually trace. Now I try to give others the same “aha!” moment I had. ⬇️ Download Excel:show more

When Ghostty detects a password input prompt, it now... changes the cursor to a lock and on macOS enables the secure input API. When the secure input API is enabled, we show a neat, animated icon that explains what's going on when clicked. Another example of native UI wins (imo). Secure Input is the macOS system API that prevents accessibility APIs from reading your keystrokes, so things like screen recording software and so on can't read your passwords. Other terminals on macOS support secure input. I think only iTerm also supports secure input on password detection. So as a disclaimer, I'm not trying to claim this as a huge innovation, I just think our implementation is nice. 😊show more

ONE PROMPT. AN ENTIRE FINANCIAL DASHBOARD. I asked a... new AI agent to build it, and it created this interactive dashboard from scratch. It planned the project, wrote the code, ran it locally, and handled the final touches. Meet EvoX Agent 🧵👇show more

I designed these worksheets to turn Agentic AI concepts... into simple math problems you can do by hand. ✍️ Download PDF: Problems 1 to 5: 1. Count the tokens: split on spaces, one word per box 2. Subword splitting: when one word is three tokens 3. Punctuation counts: the marks are tokens too 4. Tokens per word: the ratio that turns words into a bill 5. Will it fit? A document against a context window Why am I making these worksheets? AI is making people (including me) think less. It's just too easy to ask AI a few questions about a new AI concept and start to believe I get it. Until recently, we could use a coding problem to practice a new AI concept. But now it has become too easy to ask AI to write the code, and we start to think we must know the concept, since we technically solved a coding problem. Thus, my approach is to recast AI concepts as simple math problems we must solve with pen and paper. Using our hands is one way to motivate ourselves to start thinking again. ✍️ ~ Prof. Tom Yehshow more

✍️ I wrote an article on programming blur shaders... for beginners. You do not need to be adept at either math or programming to understand how it works :) Going from the most basic/straightforward type of blur, to what you see below, and more! Lots of pretty pictures, media, and interactive code to learn from. -- Box blur, with clipping and radial weighting. (So, no longer really a box blur...?) 🔍 #gamedev #indiedev #unity3dshow more

here's how you can create videos with full camera... control using Krea Agent: - take an input image and ask the agent to create a 3D scene with it. - after the scene is created, ask it to create any camera movement you want. - finally, ask it to render the 3D video with Seedance 2.5. try it now 👇show more

How to combo into Luminous Illusion (with slowdown to... show the speed). Luminous Illusion is a Raging Demon input (LP LP → LK HP). Kaji being able to consistently do this and in even harder situations to confirm still messes with my headshow more

Here’s half a dozen telesnaps fed to a AI... with no other input. Yes, it’s obviously an uncanny mess, and I know AI stuff is a controversial topic, but this route for recons definitely has future potential as image-to-video continues to improve.show more

Two months ago, at an RSS workshop panel, I... said that general real2sim reconstruction is still far from solved, especially for articulated objects, which will be a major bottleneck for robotics. But now that has totally changed with Astra; using several photos as input, we can easily reconstruct vivid articulated scenes. The result is so impressive! Excited to see how it will shift the paradigm of real2sim2real and agentic learning for robotics and humanoids.show more