Encoder For each input word, we encode It's position (in the input text). Since Transformer is not an RNN, the sequence aspect can get lost. So instead, here we encode the position explicitly. Evaluate 'self-attention' - what other OUTPUT words might matter Evaluate attention to encoded representations of the INPUT words --> this is the extra step in decoder (vs. encoder) Put it through a...
A lot of data in the world has sequence.. ie a temporal aspect. Eg. music, spoken language. By treating each data point independently (in a feed-forward only mode) we lose the ability to model the sequential aspect of it. In Recurrent Neural Network , computation of the neuron is a product of both the current input and this past memory of previous time steps. So it has a constant relation back...
A transformer is the major breakthrough of recent times - a neural network architecture that uses attention to process all tokens in parallel instead of step-by-step like an RNN. Processes sequences in parallel Built from stacked blocks of attention + feedforward layers Scales very well with data and compute (better for long texts + GPUs/TPUs)) Why are they better RNNs have sequential...
I first heard Ethan Mollick on The Ezra Klein Show in April 2024 (“How Should I Be Using A.I. Right Now?”). He offered sensible, practical ways to use AI without the hype. Shortly after, I read Co-Intelligence and have followed his writing and talks since. In a recent interview with Sana Labs founder and CEO Joel Hellermark, Mollick argued that the traditional apprenticeship path is shifting in...
AI voice dictation is having a moment. These tools do more than transcribe—they read context, add punctuation, and learn your style. Many creators say they work two to three times faster. Two weeks ago I started using Wispr Flow Pro. Here is what I found. The Good There is no doubt this has been a real productivity boost. It does not feel like the old dictation tools because the AI cleans up...
Gradient descent is an iterative algorithm for minimizing a loss function by moving the model parameters in the direction that most rapidly decreases the loss. Process: Start initially with random weights for all inputs. Compute the loss. Calculate the gradient of loss with respect to that initial setting of weights. In one-dimension, gradient is basically the derivative In multi-dimension,...
Backpropagation is the main algorithm used for training neural networks with hidden layers. The main idea is that you can calculate an estimate for how much the error in the output node is based on the errors in the weights of the node before it. It does so by: Starting with the error in the output layer, calculate the gradient descent for the weights of the previous layer Propagate error back...
Dharmesh's post made me realize there’s a name for something I’ve been doing implicitly for a while—using AI to help me write better prompts. Strictly speaking, that’s AI-assisted prompt refinement. There’s a closely related idea called metaprompting—writing prompts that generate other prompts—which also makes a real difference, especially for deeper research. These omniscient models have been...
Given an input and its correct (target) output, a loss function compares the model’s prediction to the target and returns a single number measuring how wrong the prediction is. That number is called the Loss Larger loss means a worse prediction; zero loss means a perfect prediction. Training a neural network means changing the parameters (weights and biases) to make this loss as small as...
Eg. Dropout Randomly and temporarily remove/shutdown some of the interstitial neurons, so that the weights only flow through a subset. This builds new-paths ways and forces the neural network to not depend on any particular neurons. Do it repeatedly, each time removing different set of neurons. Eg. Early Stopping Stop when the test loss has plateaued, just before it starts increasing again....