Full metadata
Title
Beyond Deep Learning: Synthesizing Navigation Programs using Neural Turing Machines
Description
This thesis aims to improve neural control policies for self-driving cars. State-of-the-art navigation software for self-driving cars is based on deep neural networks, where the network is trained on a dataset of past driving experience in various situations. With previous methods, the car can only make decisions based on short-term memory. To address this problem, we proposed that using a Neural Turing Machine (NTM) framework adds long-term memory to the system. We evaluated this approach by using it to master a palindrome task. The network was able to infer how to create a palindrome with 100% accuracy. Since the NTM structure proves useful, we aim to use it in the given scenarios to improve the navigation safety and accuracy of a simulated autonomous car.
Date Created
2018-05
Contributors
- Martin, Sarah (Author)
- Ben Amor, Hani (Thesis director)
- Fainekos, Georgios (Committee member)
- Barrett, The Honors College (Contributor)
Topical Subject
Resource Type
Extent
25 pages
Language
Copyright Statement
In Copyright
Primary Member of
Series
Academic Year 2017-2018
Handle
https://hdl.handle.net/2286/R.I.50206
Level of coding
minimal
Cataloging Standards
System Created
- 2018-08-21 01:56:24
System Modified
- 2021-07-15 10:18:27
- 3 years 2 months ago
Additional Formats