Practice of Deep Learning
About This Course
This course serves as an introduction to deep learning and introduces the PyTorch framework to students, which is the most used Python framework for prototyping Neural Networks and Deep Learning models. During this course, the students will study the implementation of a shallow neural network, and discuss typical issues and good practices related to training such models. By the end of the course, the students will be able to implement and train a simple neural network using a simple tabular dataset. This course assumes that students have a programming background in Python, along with a basic knowledge of linear algebra, optimization and machine learning.
What You'll Learn
• implement neural networks using the PyTorch framework, to simplify the development of said models.
• understand and implement the forward and backward propagation mechanisms that are used to evaluate and train neural networks.
• tune neural networks by implementing advanced initializers, optimizers, loss functions and regularization.
• understand the concepts of generalization, over- and underfitting, exploding and vanishing gradients.
• implement good professional practices for training and evaluating deep learning models, such as train/test/validation sets, saver/loader functions, etc.
Entry Requirements
Participants should possess a basic understanding of the Python programming language and ideally should have gone through a Machine Learning course. If students already have a background in data science/machine learning, this requirement can be lifted.