Practical Guide to Neural Network Training: Working with Leading Frameworks

Today’s deep learning frameworks make it easier than ever to work with neural networks. This course will teach you how to efficiently build and train a neural network, while evaluating and addressing some common challenges.

Machine learning is the secret behind today’s most innovative applications. The ability to build and fine-tune neural networks has become an indispensable skill in this new age of artificial intelligence. In this course, Practical Guide to Neural Network Training: Working with Leading Frameworks, you'll gain the ability to train neural networks effectively and efficiently. First, you'll explore popular deep learning frameworks, such as TensorFlow and PyTorch, getting hands-on experience with PyTorch and using it to preprocess data, build a neural network, and then train the model. Next, you’ll discover how to monitor the training progress and evaluate the performance of the neural network using a validation dataset. Finally, you’ll learn common challenges in training neural networks -- such overfitting/underfitting and vanishing/exploding gradients -- and learn strategies to balance these issues. When you're finished with this course, you'll have the skills and knowledge needed to confidently build and train your own neural networks using popular frameworks.

• Course Overview 2mins
• Training a Basic Neural Network with PyTorch 18mins
• Challenges: Overfitting, Underfitting, and Vanishing/Exploding Gradients 9mins