Holberton School Specialization Track
| Learning Objectives: Math for Machine Learning |
|---|
Scalars, vectors, matrices, and tensors |
The Dot product and matrix multiplication |
Matrix identities, inverses, and determinants |
Normalization |
Scatter and contour plots |
Line and bar graphs |
Summation and product notation |
Derivatives and partial derivatives |
The chain and product rules |
Eigenvalues and Eigenvectors |
Single value decomposition |
Marginal and conditional probabilities |
Expectation, standard deviation, variance, and covariance |
Probability distributions |
Bayesian probability |
Mixture models |
| Learning Objectives: Supervised Learning |
|---|
Multi-layered networks |
Forward and back propagation |
Stochastic gradient descent |
Weight and bias initialization |
Bias and variance tradeoff |
Regularization |
Hyperparameter optimization |
Convolutional neural networks |
ResNets |
Deep convolutional architectures |
Recurrent neural networks |
Deep recurrent architectures |
| Learning Objectives: Unsupervised Learning |
|---|
Principal component analysis |
Clustering |
Embeddings |
Autoencoders |
Bayesian optimization |
Hidden Markov Models |
| Learning Objectives: Data Management |
|---|
Web scraping |
Data labeling |
Avoiding human bias |
SQL databases |
Query optimization |
Map reduce |
Ekaterina Kalache: github account, twitter