Knowledge map Every page names what to read before it. Here is the whole library at once: a dot for each page, its topic down the side, and how far it stands from a starting point across. Pick a dot to see the way to it.
Pages 126
Links between them 121
The longest way in 13 pages The board: every page, by topic and by distance from a starting point Start 1 2 3 4 5 6 7 8 Steps from a starting point → Mathematics 4 Statistics 15 Metrics & losses 21 Optimization 8 Machine learning 30 Deep learning 16 Computer vision 13 NLP 17 Tooling 2 1 2 3 Gradient Expectation and variance Eigenvectors and eigenvalues Hypothesis testing Bayes' theorem A/B testing Time series decomposition MSE Confusion matrix MAE Intersection over union Decision tree KNN PCA K-means Train-test split Image classification Tokenization Natural language processing Jupyter Notebook Machine learning workflow Entropy Correlation Outliers Stationarity Confidence interval Confounding Maximum likelihood Multiple comparisons Accuracy Huber loss MAPE MSLE Precision R² Recall RMSE Specificity BLEU Gradient descent Missing data Class imbalance Linear regression Distance-weighted KNN Manifold learning SVM Backpropagation Bag of words Language model Named entity recognition Word embeddings Autocorrelation Bootstrap Central limit theorem Cross-entropy Mean average precision F1-score ROC AUC Perplexity BFGS Conjugate gradient Learning rate SGD Regularization Feature engineering Logistic regression Overfitting Polynomial regression Perceptron Recurrent neural network Generative adversarial network Decoding Prompting TF-IDF Attention Sentence embeddings Generalized linear models Model calibration Adam Mini-batch gradient descent Early stopping Gaussian discriminant analysis → Lasso regression Ridge regression Bagging Boosting Bias-variance tradeoff Cross-validation Dropout Convolution Sigmoid Data augmentation PointNet Diffusion model Sequence-to-sequence Hallucination Instruction tuning Retrieval-augmented generation Fréchet Inception Distance Gradient boosting Bayesian linear regression Elastic Net Random forest Data leakage Hyperparameter tuning Batch normalization Depthwise separable convolution Pooling Receptive field ReLU Softmax Tanh Transposed convolution Convolutional neural network Feature importance Residual connection Leaky ReLU Object detection Self-supervised learning Semantic segmentation Transfer learning Instance segmentation Transformer Vision transformer BERT CLIP The way to Gaussian discriminant analysis 3 pages to read first Machine learning · difficulty 4/5
A classifier that models what each class's data looks like — fitting a Gaussian per class — and then uses Bayes' rule to turn that into a prediction.
What builds on it Nothing builds on it yet.