classroom course
Deep Learning Course with TensorFlow, Keras and PyTorch
Price
1.430 € + VAT
Duration
16 hours
Data:
July 04th-05th
Qualification obtained
Certificate
Course code
AGSAI003
TensorFlow, Keras and PyTorch are among the most used libraries in Research & Development and in the Industry world for the implementation of Neural Networks. This course represents an introductory guide to using these libraries. We will start from the concept of Tensor and carry on with the development and training of a Neural Network. Each library will be described by means of examples and there will be a comparison of the main features and differences, which one to choose depending on the applications, their pros and cons.
The course is aimed at:
- programmers
- graduate students who know programming
Tensorflow/Keras – Pytorch course
- 1. The fundamentals of Machine Learning
- 1.1 What is Machine Learning and when to use it
- 1.2 Types of Machine Learning algorithm
- 1.2.1 Supervised Learning
- 1.2.2 Unsupervised Learning
- 2. Neural Networks e Deep Learning
- 2.1 Introduction to Neural Networks
- 2.2 Multi layer perceptron
- 2.3 Convolutional Neural Networks
- 2.4 Recurrent neural networks
- 2.4 Other architectures (Autoencoder, GAN, Transformers)
- 3. Training Neural Networks
- 3.1 Vanishing/Exploding Gradients
- 3.2 Re-use of Pre-trained Layers
- 3.3 Optimizers
- 3.4 Overfitting e Regularization
- 4. Design Neural Networks with Tensorflow 2.0
- 4.1 Tensorflow Overview
- 4.2 MLP with Tensorflow
- 4.3 ConvNet with Tensorflow
- 4.4 Recurrent Networks with Tensorflow
- 4.5 Other Architectures
- 5. Design Neutral Networks with PyTorch
- 5.1 Pytorch Overview
- 5.2 MLP with PyTorch
- 5.3 ConvNet with PyTorch
- 5.4 Recurrent Networks with Pytorch
- 5.5 Other Architectures
- 6. Advanced Topics with Tensorflow and Pytorch
- 6.1 Memory management
- 6.2 Training on GPUs
- 6.3 Training on Google Colab
TensorFlow, Keras and PyTorch are among the most used libraries in Research & Development and in the Industry world for the implementation of Neural Networks. This course represents an introductory guide to using these libraries. We will start from the concept of Tensor and carry on with the development and training of a Neural Network. Each library will be described by means of examples and there will be a comparison of the main features and differences, which one to choose depending on the applications, their pros and cons.
The course is aimed at:
- programmers
- graduate students who know programming
Tensorflow/Keras – Pytorch course
- 1. The fundamentals of Machine Learning
- 1.1 What is Machine Learning and when to use it
- 1.2 Types of Machine Learning algorithm
- 1.2.1 Supervised Learning
- 1.2.2 Unsupervised Learning
- 2. Neural Networks e Deep Learning
- 2.1 Introduction to Neural Networks
- 2.2 Multi layer perceptron
- 2.3 Convolutional Neural Networks
- 2.4 Recurrent neural networks
- 2.4 Other architectures (Autoencoder, GAN, Transformers)
- 3. Training Neural Networks
- 3.1 Vanishing/Exploding Gradients
- 3.2 Re-use of Pre-trained Layers
- 3.3 Optimizers
- 3.4 Overfitting e Regularization
- 4. Design Neural Networks with Tensorflow 2.0
- 4.1 Tensorflow Overview
- 4.2 MLP with Tensorflow
- 4.3 ConvNet with Tensorflow
- 4.4 Recurrent Networks with Tensorflow
- 4.5 Other Architectures
- 5. Design Neutral Networks with PyTorch
- 5.1 Pytorch Overview
- 5.2 MLP with PyTorch
- 5.3 ConvNet with PyTorch
- 5.4 Recurrent Networks with Pytorch
- 5.5 Other Architectures
- 6. Advanced Topics with Tensorflow and Pytorch
- 6.1 Memory management
- 6.2 Training on GPUs
- 6.3 Training on Google Colab