Search
Skip to Search Results- 6Neural Networks
- 4Machine Learning
- 1Admissible Heuristics
- 1CatSyn
- 1Coagent Networks
- 1Convolutional LSTM
-
Fall 2023
The problem of missing data is omnipresent in a wide range of real-world datasets. When learning and predicting on this data with neural networks, the typical strategy is to fill-in or complete these missing values in the dataset, called impute-then-regress. Much less common is to attempt to...
-
Spring 2019
In this thesis we introduce a new loss for regression, the Histogram Loss. There is some evidence that, in the problem of sequential decision making, estimating the full distribution of return offers a considerable gain in performance, even though only the mean of that distribution is used in...
-
Fall 2022
Machine learning has been used to solve single-agent search problems. One of its applications is to guide search algorithms by learning heuristics. However, it is difficult to provide guarantees on the quality of learning from a neural network, since the resulting heuristics can be inadmissible,...
-
Fall 2021
Structural credit assignment in neural networks is a long-standing problem, with a variety of alternatives to backpropagation proposed to allow for local training of nodes. One of the early strategies was to treat each node as an agent and use a reinforcement learning method called REINFORCE to...
-
Fall 2019
Dialogue systems, also known as Conversational Agent (CA), are designed to mimic coherent conversations with humans. Most conversational agents are specialized for a specific domain such as travel booking and are typically finite state-based or template-based. Open domain dialogue systems have...
-
Spring 2021
This thesis evaluated Convoultional LSTM (ConvLSTM) for frame prediction to help better understand motion in neural networks. Three different neural networks were implemented and trained. The three networks included, the original ConvLSTM paper by Shi et al. [35], the Spatio-Temporal network by...