Implementing (almost!) from scratch some AI/ML algorithms. This is a repository of some implementations found online (all referenced) with some occasional additional modifications/comments.
- Backpropagation
- Building a Deep Learning Framework
- Building a DL framework for the MNIST dataset
- PDP = Partial Dependence Plot
- Attention Mechanism
- Bagging
- Classifier Calibration
- Decision Trees
- Gradient Boosting
- k-Means
- k-Nearest
- Learning Vector Quantization = LVQ
- Linear Regression
- Logistic Regression
- Naive Bayes Classifier
- PCA = Principal Component Analysis
- Random Forest
- Softmax Regression
- Chi-square feature selection
- Student’s t-Test
- Bernoulli and Multinomial Naive Bayes
- Adam optimiser
- Bayesian Optimiser
- Differential Evolution
- Evolution Strategies
- Genetic Algorithm
- Simulated Annealing
- LU Decomposition
- Cholesky Decomposition
- QR Decomposition
- Jacobi Method
- labml.ai Deep Learning Paper Implementations This is a collection of simple PyTorch implementations of neural networks and related algorithms.