Python - Neural networks

• Knowledge of Python programming at the PYTHON_INTRO course level, but knowledge at the PYTHON_ADV course level is an advantage
• Knowledge of the basics of data analysis at the level of the PYTHON_DATAAN course
• Knowledge of the basics of machine learning at the level of the PYTHON_ML_INTRO course

• Professional explanation with practical examples, exercises on computers.

• Presentation of the subject matter in printed or online form.

Day 1:

• Introduction to neural networks and machine learning
• Basics of linear and logistic regression
• Activation functions for neural networks (sigmoid, ReLU, etc.)
• Design and implementation of a simple one-layer neural network

Day 2:

• Introduction to the TensorFlow library
• Design and implementation of a multilayer neural network using TensorFlow
• Neural network training and performance verification
• Solving the problem of overtraining

Day 3:

• Introduction to convolutional neural networks (CNN)
• Basics of image processing and convolution
• Implementation of a simple CNN on the MNIST dataset
• Visualization and interpretation of results

Day 4:

• Recurrent Neural Networks (RNN)
• Basics of processing sequences and time series
• Implementation of a simple RNN on the stock price forecasting dataset
• Visualization and interpretation of results

Day 5:

• Introduction to autoencoders
• Basics of random models
• Implementation of a simple autoencoder on the MNIST dataset
• Visualization and interpretation of results

Previous courses

Python - Introduction to Machine Learning [PYTHON_ML]

Python I - introduction to programming [PYTHON_INTRO]

Next courses

Python - Convolutional neural networks [PYTHON_ML_CNN]

Python - Backpropagation in neural networks [PYTHON_ML_BP]

Python - Deep Learning [PYTHON_ML_DP]