Introduction to neural networks, introduction of basic concepts of neural networks, their history, and their use compared to traditional machine learning methods.

Introduction to TensorFlow and Keras in the Python programming environment, cloud computing.

Perceptrons and multi-layer perceptrons. Explanation of the perceptron model, its capabilities and limitations, and the transition to multi-layer perceptrons (MLP).

Back-promotion errors. A detailed exploration of the back-propagation algorithm used to compute gradients for the training process.

Optimization algorithms. A survey of various optimization algorithms used for training neural networks, including stochastic gradient descent and Adam.

Hyperparameters: search for optimal settings of neural network parameters (grid search, random grid search and Bayes methods).

Convolutional Neural Networks (CNN). Introduction to CNNs, their architecture, and applications in image processing and pattern recognition.

Recurrent Neural Networks (RNN). Introduction to the basics of RNNs, including variants such as LSTM and GRU, and their use for sequential data.

Regularization and Dropout. Explanation of techniques such as regularization and dropout to prevent re-learning of neural network models.

Deep Reinforcement Learning, Introduction to Deep Reinforcement Learning, its principles and applications in adaptive systems and games.

Autoencoders and Generative Adversarial Networks (GANs). Overview of autoencoders and GANs, key concepts, and their use for generating new data.

Practical aspects of training neural networks. Discussion on hyperparameter selection, architecture setup, and performance evaluation of neural networks.

Applications of neural networks. Examples of real-world applications of neural networks in industry, healthcare, and other fields.