Find
Search for over 200,000 study notes and past assignments!
Swap
Download study resources by swapping your own or buying Exchange Credits.
Study
Study from your library anywhere, anytime.
CS5242 Group Report: Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs)
CS5242 - Neural Networks and Deep Learning
42 Pages • Essays / Projects • Year Uploaded: 2022
Multi-layer perceptron (MLP) is a classical example of neural networks, simple and provide us great understanding of the concepts in this field of machine learning. While MLPs work well for simple datasets and tasks, they become insufficient for more complex tasks such as computer vision and natural language processing. The former often required learning features of image, which can explode the number of parameters needed to train MLPs, while the later requires sequence processing that classical MLPs do not possess. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are better choice for these two high level tasks. CNNs are the go-to method for predictive modelling of images as they can extract patterns, location invariantly, in images and understand the spatial relations in data well (pixels in images). CNNs might be used for text-based tasks and this will be shown in this project. RNNs on the other hand, are geared with persistence unit that allow good modeling of temporal relations, which gives it good performance in sequence predicting like NLP applications. In this assignment, the construction, and effects of various hyperparameters on the performance of these 2 types of network will be investigated.
This document is 20 Exchange Credits
More about this document:
|
This document has been hand checkedEvery document on Thinkswap has been carefully hand checked to make sure it's correctly described and categorised. No more browsing through piles of irrelevant study resources. |
|
This is an Essay / ProjectEssays / Projects are typically greater than 5 pages in length and are assessments that have been previously submitted by a student for academic grading. |
|
What are Exchange Credits?Exchange Credits represent the worth of each document on Thinkswap. In exchange for uploading documents you will receive Exchange Credits. These credits can then be used to download other documents for free. |
|
Satisfaction GuaranteeWe want you to be satisfied with your learning, that’s why all documents on Thinkswap are covered by our Satisfaction Guarantee. If a document is not of an acceptable quality or the document was incorrectly described or categorised, we will provide a full refund of Exchange Credits so that you can get another document. For more information please read Thinkswap's Satisfaction Guarantee. |
Studying with Academic Integrity
Studying from past student work is an amazing way to learn and research, however you must always act with academic integrity.
This document is the prior work of another student. Thinkswap has partnered with Turnitin to ensure students cannot copy directly from our resources. Understand how to responsibly use this work by visiting ‘Using Thinkswap resources correctly’.