Machine Learning

Module of Machine Learning , carried out during Software Engineering studies at Holberton School.

Technologies

All of the following folders are projects done during the studies:

Project name	Description
`math/0x00-linear_algebra`	It aims to learn about vectors, matrices, transposes, dot product, matriz multiplication and NumPy
`math/0x01-plotting`	It aims to learn about plot, scatter plot, line graph, bar graph, histogram and `matplotlib`
`math/0x02-calculus`	It aims to learn about summation and product notation, series, derivative, chain rule, partial derivative and integrals.
`math/0x03-probability`	It aims to learn about probability, independence, union, intersection, probability distributions (PDF & PMF), cumulative distribution function, percentile, mean, standard deviation and variance.
`supervised_learning/0x00-binary_classification`	It aims to learn about models, supervised learning, prediction, nodes, weight, bias, activation functions, layers, logistic regression, loss and cost functions.
`supervised_learning/0x01-multiclass_classification`	It aims to learn about multiclass classification, one-hot vector, softmax function, cross-entropy loss and pickling.
`supervised_learning/0x02-tensorflow`	It aims to learn graphs, sessions, tensors, placeholders, operations, namespaces, training and checkpoints on Tensorflow
`supervised_learning/0x03-optimization`	It aims to learn hypermarameters, saddle points, normalizing data, stochastic gradient descent, mini-batch gradient descent, moving average, RMSProp, Adam optimization, learning rate decay and batch normalization