tailieunhanh - Lecture Machine learning (2014-2015) - Lecture 7: Backpropagation: A modular approach (Torch NN)

This lecture describes modular ways of formulating and learning distributed representations of data. The objective is for you to learn: How to specify models such as logistic regression in layers; how to formulate layers and loss criterions; how well formulated local rules results in correct global rules; how back-propagation works; how this manifests itself in Torch. | Outline of the lecture This lecture describes modular ways of formulating and learning distributed representations of data. The objective is for you to learn How to specify models such as logistic regression in layers. How to formulate layers and loss criterions. How well formulated local rules results in correct global rules. How back-propagation works. How this manifests itself in .

TỪ KHÓA LIÊN QUAN