Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Ashwin Srinivasan

Ashwin Srinivasan

Composition of Relational Features with an Application to Explaining Black-Box Predictors



Ashwin Srinivasan , A Baskar , Tirtharaj Dash , Devanshu Shah

Figure 1 for Composition of Relational Features with an Application to Explaining Black-Box Predictors
Figure 2 for Composition of Relational Features with an Application to Explaining Black-Box Predictors
Figure 3 for Composition of Relational Features with an Application to Explaining Black-Box Predictors
Figure 4 for Composition of Relational Features with an Application to Explaining Black-Box Predictors
* 45 pages, submitted to Machine Learning Journal 
   Access Paper or Ask Questions

One-way Explainability Isn't The Message



Ashwin Srinivasan , Michael Bain , Enrico Coiera

Figure 1 for One-way Explainability Isn't The Message
Figure 2 for One-way Explainability Isn't The Message
Figure 3 for One-way Explainability Isn't The Message
Figure 4 for One-way Explainability Isn't The Message
* (22 pages. Submitted for review as a Perspectives paper to Nature Machine Intelligence) 
   Access Paper or Ask Questions

Solving Visual Analogies Using Neural Algorithmic Reasoning



Atharv Sonwane , Gautam Shroff , Lovekesh Vig , Ashwin Srinivasan , Tirtharaj Dash

Figure 1 for Solving Visual Analogies Using Neural Algorithmic Reasoning
Figure 2 for Solving Visual Analogies Using Neural Algorithmic Reasoning
Figure 3 for Solving Visual Analogies Using Neural Algorithmic Reasoning
Figure 4 for Solving Visual Analogies Using Neural Algorithmic Reasoning
* 20 pages. Contains extended abstract accepted at the AAAI-22 Student Abstract and Poster Program along with relevent supplementary material 
   Access Paper or Ask Questions

Using Program Synthesis and Inductive Logic Programming to solve Bongard Problems



Atharv Sonwane , Sharad Chitlangia , Tirtharaj Dash , Lovekesh Vig , Gautam Shroff , Ashwin Srinivasan

Figure 1 for Using Program Synthesis and Inductive Logic Programming to solve Bongard Problems
Figure 2 for Using Program Synthesis and Inductive Logic Programming to solve Bongard Problems
Figure 3 for Using Program Synthesis and Inductive Logic Programming to solve Bongard Problems
* Equal contribution from first two authors. Accepted at the 10th International Workshop on Approaches and Applications of Inductive Programming as a Work In Progress Report 
   Access Paper or Ask Questions

Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations



Ji Xin , Chenyan Xiong , Ashwin Srinivasan , Ankita Sharma , Damien Jose , Paul N. Bennett

Figure 1 for Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations
Figure 2 for Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations
Figure 3 for Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations
Figure 4 for Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations

   Access Paper or Ask Questions

How to Tell Deep Neural Networks What We Know



Tirtharaj Dash , Sharad Chitlangia , Aditya Ahuja , Ashwin Srinivasan

Figure 1 for How to Tell Deep Neural Networks What We Know
Figure 2 for How to Tell Deep Neural Networks What We Know
Figure 3 for How to Tell Deep Neural Networks What We Know
Figure 4 for How to Tell Deep Neural Networks What We Know
* 12 pages (full version); substantial overlap with arXiv:2103.00180 
   Access Paper or Ask Questions

Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment



Tirtharaj Dash , Ashwin Srinivasan , A Baskar

Figure 1 for Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
Figure 2 for Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
Figure 3 for Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
Figure 4 for Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
* submitted to Machine Learning Journal (MLJ) 
   Access Paper or Ask Questions

Incorporating Domain Knowledge into Deep Neural Networks



Tirtharaj Dash , Sharad Chitlangia , Aditya Ahuja , Ashwin Srinivasan

Figure 1 for Incorporating Domain Knowledge into Deep Neural Networks
Figure 2 for Incorporating Domain Knowledge into Deep Neural Networks
* Submitted to IJCAI-2021 Survey Track (6+2 pages) 
   Access Paper or Ask Questions

Constructing and Evaluating an Explainable Model for COVID-19 Diagnosis from Chest X-rays



Rishab Khincha , Soundarya Krishnan , Krishnan Guru-Murthy , Tirtharaj Dash , Lovekesh Vig , Ashwin Srinivasan

Figure 1 for Constructing and Evaluating an Explainable Model for COVID-19 Diagnosis from Chest X-rays
Figure 2 for Constructing and Evaluating an Explainable Model for COVID-19 Diagnosis from Chest X-rays
Figure 3 for Constructing and Evaluating an Explainable Model for COVID-19 Diagnosis from Chest X-rays
Figure 4 for Constructing and Evaluating an Explainable Model for COVID-19 Diagnosis from Chest X-rays

   Access Paper or Ask Questions
1
2
>>