Intermediate
A little maths, a lot of intuition.
Look under the bonnet. You'll see how models actually find good parameters, how to tell if a model is any good, and the classic architectures for images, sequences and meaning.
0/7 done
- ๐ Lines and curves: regressionThe humble straight line is the ancestor of every neural network. Linear and logistic regression, explained.
- โท๏ธ Gradient descent: rolling downhillHow models find good weights: feel the slope, take a small step down, repeat.
- ๐ฅฃ Overfitting & the Goldilocks modelToo simple misses the pattern, too complex memorises the noise. How to land just right.
- ๐ฏ Is my model any good?Accuracy can lie. Meet the confusion matrix, precision, recall and F1.
- โฉ๏ธ Backpropagation: blame, passed backwardsHow a network with millions of weights figures out which ones to adjust.
- ๐๏ธ Seeing and remembering: CNNs & RNNsSpecial network shapes for images and sequences, and why they mattered.
- ๐บ๏ธ Embeddings: meaning as mapsHow AI turns words, images and songs into points in space where closeness means similarity.