Understanding the Decision Making Process of Deep Neural Networks

Understanding the Decision Making Process of Deep Neural Networks

Devinder Kumar

Devinder Kumar

Waterloo, Ontario

In this work, we propose a new approach to visualize and understand the decisions made by deep neural network.

Artificial Intelligence

  • 0 Collaborators

  • 1 Followers

    Follow

Description

In this work, we propose CLass-Enhanced Attentive Response (CLEAR): an approach to visualize and understand the decisions made by deep neural networks (DNNs) given a specific input. CLEAR facilitates the visualization of attentive regions and levels of interest of DNNs during the decision-making process. It also enables the visualization of the most dominant classes associated with these attentive regions of interest. As such, CLEAR can mitigate some of the shortcomings of heatmap-based methods associated with decision ambiguity, and allows for better insights into the decision-making process of DNNs. Quantitative and qualitative experiments across three different datasets demonstrate the efficacy of CLEAR for gaining a better understanding of the inner workings of DNNs during the decision-making process.

Gallery

Links

Paper

Me car

Devinder K. added photos to project Understanding the Decision Making Process of Deep Neural Networks

Medium 107c7d5c b808 4c80 b0c2 e9c7efb29942

Understanding the Decision Making Process of Deep Neural Networks

In this work, we propose CLass-Enhanced Attentive Response (CLEAR): an approach to visualize and understand
the decisions made by deep neural networks (DNNs) given a specific input. CLEAR facilitates the visualization
of attentive regions and levels of interest of DNNs during the decision-making process. It also enables the visualization
of the most dominant classes associated with these attentive regions of interest. As such, CLEAR can mitigate
some of the shortcomings of heatmap-based methods associated with decision ambiguity, and allows for better insights
into the decision-making process of DNNs. Quantitative and qualitative experiments across three different
datasets demonstrate the efficacy of CLEAR for gaining a better understanding of the inner workings of DNNs during
the decision-making process.

Me car

Devinder K. added photos to project Understanding the Decision Making Process of Deep Neural Networks

Medium 2c89d1fc d576 4086 8d82 85a32832a6ea

Understanding the Decision Making Process of Deep Neural Networks

In this work, we propose CLass-Enhanced Attentive Response (CLEAR): an approach to visualize and understand
the decisions made by deep neural networks (DNNs) given a specific input. CLEAR facilitates the visualization
of attentive regions and levels of interest of DNNs during the decision-making process. It also enables the visualization
of the most dominant classes associated with these attentive regions of interest. As such, CLEAR can mitigate
some of the shortcomings of heatmap-based methods associated with decision ambiguity, and allows for better insights
into the decision-making process of DNNs. Quantitative and qualitative experiments across three different
datasets demonstrate the efficacy of CLEAR for gaining a better understanding of the inner workings of DNNs during
the decision-making process.

Medium me car

Devinder K. created project Understanding the Decision Making Process of Deep Neural Networks

Medium 2c89d1fc d576 4086 8d82 85a32832a6ea

Understanding the Decision Making Process of Deep Neural Networks

In this work, we propose CLass-Enhanced Attentive Response (CLEAR): an approach to visualize and understand the decisions made by deep neural networks (DNNs) given a specific input. CLEAR facilitates the visualization of attentive regions and levels of interest of DNNs during the decision-making process. It also enables the visualization of the most dominant classes associated with these attentive regions of interest. As such, CLEAR can mitigate some of the shortcomings of heatmap-based methods associated with decision ambiguity, and allows for better insights into the decision-making process of DNNs. Quantitative and qualitative experiments across three different datasets demonstrate the efficacy of CLEAR for gaining a better understanding of the inner workings of DNNs during the decision-making process.

No users to show at the moment.