Index Catalog // ScholarsArchive@OSU

Start Over

Filtering by: Creator Dawson, Robert E. Contributor Li, Fuxin License All rights reserved

Toward Disentangling the Activations of the Deep Networks via Low-dimensional Embedding and Non-negative Factorization

Creator:

Khorram, Saeed

Abstract:

In this thesis, we introduce a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by embedding a high-dimensional activation vector of a deep network layer non-linearly into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can...

Resource Type:

Masters Thesis

Full Text:

(xTW + b); σ(x) = 1 1 + e−x (2.1) loss(ŷ, y) = −y log(ŷ)− (1− y) log(1− ŷ) In the above
Leveraging Structures of the Data in Deep Learning

Creator:

Li, Xingyi

Abstract:

The performance of deep learning frameworks could be significantly improved through considering the particular underlying structures for each dataset. In this thesis, I summarize our three work about boosting the performance of deep learning models through leveraging structures of the data. In the first work, we theoretically justify that, for...

Resource Type:

Dissertation

Full Text:

40 50 Figure 2.1: Covariance analysis on natural im- ages where ĜN (F ) = E [ supf∈F 2 N ∑N i=1
Characterizing and Addressing Dataset Shift with Deep Learning

Creator:

Olson, Matthew L.

Abstract:

This dissertation delves into understanding, characterizing, and addressing dataset shift in deep learning, a pervasive issue for deployed machine learning systems. Integral aspects of the problem are examined: We start with the use of counterfactual explanations in order to characterize the behavior of deep reinforcement learning agents in visual input...

Resource Type:

Dissertation

Full Text:

overview of our architecture, which consists of the encoder 𝐸 , gen- erator 𝐺, discriminator 𝐷 and pre