How do networks learn from errors?
Loss as a landscape, gradient descent and backpropagation.
Transcript
The model's error is summed up in one number, the loss. Learning means making it smaller.
Picture the loss as a landscape over the weights. Low ground means a better model.
At any point, the gradient is the slope. It points uphill, so we step the opposite way.
The step size is the learning rate. Too small is slow, and too large overshoots.
A forward pass makes a prediction. Comparing it with the answer gives the error.
Backpropagation sends the error backwards, finding each weight's share of the blame.
Every weight then takes a small step downhill. Repeat, millions of times.
Predict, measure the error, send it backwards, and step downhill. Repeat that, and a network learns.
More in this series
1:14How does AI work?
Neurons and weights, learning from mistakes, and predicting the next word.
1:13How does AI read a sentence?
Tokens, embeddings and attention, stacked in layers to score the next token.
1:17What are billions of parameters?
What a parameter is, how big a billion is, and why big models need racks of GPUs.
1:24How is a chatbot trained?
Pretraining, fine-tuning and human feedback turn a text predictor into an assistant.
1:23What does temperature do?
Scores become probabilities, and temperature sharpens or flattens them.
1:19How does AI draw pictures?
Diffusion models add noise to learn, then remove it to create, steered by a prompt.
1:15How can AI use your own documents?
Retrieval-augmented generation: embed, retrieve, augment the prompt, generate.
1:14Why does AI make things up?
Likely is not the same as true: gaps, snowballing errors, and what helps.
1:16How much can an AI remember?
The context window, forgetting, the cost of long inputs, and workarounds.
1:09What is an AI agent?
A model in a loop with tools and guardrails.
1:12Can AI be biased?
Skewed data, where bias comes from, proxies, and how to audit and fix it.
1:10What is overfitting?
Underfit, good fit and overfit curves, train vs test error, and the fixes.