Amit Mate, the founder and CEO of GMAC Intelligence, presents the “Fundamentals of Training AI Models for Computer Vision Applications” tutorial at the May 2023 Embedded Vision Summit.
In this presentation, Mate introduces the essential aspects of training convolutional neural networks (CNNs). He discusses the prerequisites for training, including models, data and training frameworks, with an emphasis on the characteristics of data needed for effective training. He also explores the model training process using visuals to explain the error surface and gradient-based learning techniques.
Mate’s discussion covers key hyperparameters, loss functions and how to monitor the health of the training process. He also addresses the common training problems of overfitting and underfitting, and offer practical rules of thumb for mitigating these issues. Finally, he introduces popular training frameworks and provides resources for further learning.
See here for a PDF of the slides.
