What's Next?
What's Next
You have implemented the foundational algorithms of machine learning from scratch — from a single linear neuron to gradient descent, k-means, and regularized regression. Here are natural next steps:
- Deep Learning — Implement backpropagation and multi-layer networks. Add batch normalisation, dropout, and Adam optimisation
- Convolutional Networks — 2D convolution, pooling, and feature maps for image classification
- Recurrent Networks — LSTMs and GRUs for sequence modelling, time series, and language
- Tree-Based Methods — Decision trees, random forests, and gradient-boosted trees (XGBoost)
- Probabilistic ML — Gaussian processes, variational autoencoders, and Bayesian inference
Further Reading
- The Elements of Statistical Learning by Hastie, Tibshirani & Friedman — The definitive statistical ML reference, freely available online
- Pattern Recognition and Machine Learning by Bishop — Bayesian perspective, rigorous treatment
- Deep Learning by Goodfellow, Bengio & Courville — Covers neural networks from perceptrons to attention
- fast.ai — Practical deep learning top-down course, highly recommended alongside theory