Intermediate · Free course
Machine Learning
Hands-on ML with real datasets, from regression to deployment.
90 lessons25 videos so far5 h 37 min of videoNotes for every lesson
What you’ll learn
- Data and features
- Classic models
- Evaluation and tuning
- Neural networks and MLOps
0 of 90 complete
Curriculum
- 1What machine learning is and the ML workflowsoon
- 2Python toolkit for MLsoon
- 3Maths 1: vectors13 min
- 4Maths 2: matrices15 min
- 5Maths 3: eigenvectors and SVD14 min
- 6Maths 4: derivatives13 min
- 7Maths 5: partial derivatives and gradients12 min
- 8Maths 6: gradient descent11 min
- 9Maths 7: probability basics11 min
- 10Maths 8: distributions17 min
- 11Maths 9: statistics for ML15 min
- 12Maths 10: likelihood and information theory13 min
- 13Exploratory data analysis14 min
- 14Data cleaning13 min
- 15Train, validation and test splits12 min
- 16Feature scaling and encoding17 min
- 17The scikit-learn API and pipelines13 min
- 18Linear regression from scratch12 min
- 19Linear regression in practice17 min
- 20Bias, variance and overfitting11 min
- 21Regularisation11 min
- 22Logistic regression from scratch15 min
- 23Logistic regression in practice and multiclass13 min
- 24Classification metrics 112 min
- 25Classification metrics 215 min
- 26Cross-validation14 min
- 27k-nearest neighbours14 min
- 28Naive Bayessoon
- 29Decision trees from scratchsoon
- 30Decision trees in practicesoon
- 31Support vector machinessoon
- 32Kernels and SVMs in practicesoon
- 33Ensembles: voting and baggingsoon
- 34Random forestssoon
- 35Boosting from scratchsoon
- 36XGBoost, LightGBM and CatBoostsoon
- 37Stacking and blendingsoon
- 38Feature engineering 1: numerical featuressoon
- 39Feature engineering 2: categories, dates and textsoon
- 40Feature selectionsoon
- 41Imbalanced datasoon
- 42Hyperparameter tuningsoon
- 43k-means from scratchsoon
- 44Hierarchical clustering and DBSCANsoon
- 45Gaussian mixture modelssoon
- 46Anomaly detectionsoon
- 47Association rulessoon
- 48PCA from scratchsoon
- 49t-SNE, UMAP and other reductionssoon
- 50Time series 1: fundamentalssoon
- 51Time series 2: classical forecastingsoon
- 52Time series 3: ML for forecastingsoon
- 53Recommender systems 1soon
- 54Recommender systems 2soon
- 55Reinforcement learning basicssoon
- 56Neural networks from scratch 1: forward passsoon
- 57Neural networks from scratch 2: backpropagationsoon
- 58PyTorch 1: tensors and autogradsoon
- 59PyTorch 2: nn.Module and the training loopsoon
- 60PyTorch 3: data loadingsoon
- 61Optimiserssoon
- 62Learning rates and initialisationsoon
- 63Regularisation for deep networkssoon
- 64Training tricks and debuggingsoon
- 65CNNs 1: convolutionssoon
- 66CNNs 2: architecturessoon
- 67Transfer learningsoon
- 68Computer vision taskssoon
- 69RNNs and sequencessoon
- 70LSTMs and GRUssoon
- 71NLP basicssoon
- 72Word embeddingssoon
- 73Seq2seq and attentionsoon
- 74Self-attention from scratchsoon
- 75Transformers from scratchsoon
- 76Pretrained transformers with Hugging Facesoon
- 77Generative modelssoon
- 78Saving and serving modelssoon
- 79Containerising and deploying modelssoon
- 80Experiment tracking and model registrysoon
- 81ML pipelines and orchestrationsoon
- 82Monitoring and driftsoon
- 83Explainabilitysoon
- 84Fairness and responsible MLsoon
- 85Interview prep 1: ML theory questionssoon
- 86Interview prep 2: coding and maths roundssoon
- 87Interview prep 3: ML system designsoon
- 88Project 1: house price predictionsoon
- 89Project 2: customer churnsoon
- 90Capstone: image classifier to productionsoon