This document outlines the basic building blocks of neural networks. It discusses dense connections, embeddings for text processing, tied weights to reduce parameters, recurrence for sequences, and convolutions for images. These building blocks can be combined to solve complex problems, like predicting house prices from house features, predicting the next word in a sequence of text, image classification to detect outdoor scenes, and image captioning that combines convolutional and recurrent neural networks.
50. BUILDING BLOCKS
1. dense connections
2. embeddings for processing text
3. tied weights for reducing parameters
4. recurrence for handling sequences
59. BUILDING BLOCKS
1. dense connections
2. embeddings for processing text
3. tied weights for reducing parameters
4. recurrence for handling sequences
5. convolutions for processing images
61. PROBLEM: CAPTIONING IMAGES
input: output:
A group of young
people playing a
game of frisbee.
Show and Tell: A Neural Image Caption Generator: Vinyals et al