Introduction to Attention-Based Neural Networks

سرفصل های دوره

Attention-based models allow neural networks to focus on the most important features of the input, thus producing better results at the output. In this course, Janani Ravi explains how recurrent neural networks work and builds and trains two image captioning models one without attention and another using attention models and compares their results. If you have some experience and understanding of how neural networks work and want to see what attention-based models can do for you, check out this course.

01 - Introduction

01 - Prerequisites

02 - What are attention-based models

03 - Attention in language generation and translation models

02 - 1. Recurrent Neural Networks to Learn Sequential Data

01 - Feed forward networks and their limitations

02 - Recurrent neural networks for sequential data

03 - The need for long memory cells

04 - LSTM and GRU cells

05 - Types of RRNNS

03 - 2. Encoder-Decoder Networks for Language Models

01 - Language generation models

02 - Sequence to sequence models for language translation

04 - 3. Attention-Based Neural Networks

01 - The role of attention in sequence to sequence models

02 - Attention mechanism in sequence to sequence models

03 - Alignment weights in attention models

04 - Bahdanau attention

05 - Attention models for image captioning

06 - Encoder decoder structure for image captioning

05 - 4. Image Captioning Model without Attention

01 - Setting up Colab and Google Drive

02 - Loading in the Flickr8k dataset

03 - Constructing the vocabulary

04 - Setting up the dataset class

05 - Implementing utility functions for training data

06 - Building the encoder CNN

07 - Building the decoder RNN

08 - Setting up the sequence to sequence model

09 - Training the image captioning model

06 - 5. Image Captioning Model Using Attention

01 - Loading the dataset and setting up utility functions

02 - The encoder CNN generating unrolled feature maps

03 - Implementing Bahdanau attention

04 - The decoder RNN using attention

05 - Generating captions using attention

06 - Training the attention-based image captioning model

07 - Visualizing the model's attention

07 - Conclusion

01 - Summary and next steps

139,000 تومان

خرید اشتراک افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: LinkedIn Learning (Lynda)