Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Learn to implement a minimal neural network toolkit for NLP in this lecture from CMU's Neural Networks for NLP course. Explore model definition, graph creation, forward and backward calculations, and parameter updates. Gain insights into neural network frameworks, deep Sibo models, and numerical computation. Discover how to work with tensors, create model code, handle weights and input dimensions, and manage computation graphs. Master the process of backward propagation and parameter updating in this comprehensive overview of building neural network tools for natural language processing tasks.
Syllabus
Introduction
Neural Network Frameworks
Deep Sibo Model
Numerical Computation
tensors
tensor data structure
algorithm sketch
model creation code
weights
input dimension
reset computation graph
computation graph
ops
backward
updating parameters
summary
Taught by
Graham Neubig