David Leake

David Leake

Indiana University Bloomington

H-index: 52

North America-United States

About David Leake

David Leake, With an exceptional h-index of 52 and a recent h-index of 16 (since 2020), a distinguished researcher at Indiana University Bloomington, specializes in the field of Case-Based Reasoning, Cognitive Science, Explanation, Intelligent User Interfaces, Neuro-Symbolic AI.

His recent articles reflect a diverse array of research interests and contributions to the field:

Bridging AI Paradigms with Cases and Networks

Towards Addressing Problem-Distribution Drift with Case Discovery

Enhancing Case-Based Reasoning with Neural Networks

Examining the Impact of Network Architecture on Extracted Feature Quality for CBR

Less is Better: An Energy-Based Approach to Case Base Competence

Combining Case-Based Reasoning with Deep Learning: Context and Ongoing Case Feature Learning Research

Large language models need symbolic AI

In Memoriam: Roger C. Schank, 1946–2023

David Leake Information

University

Position

Professor of Computer Science

Citations(all)

9498

Citations(since 2020)

1326

Cited By

8571

hIndex(all)

52

hIndex(since 2020)

16

i10Index(all)

139

i10Index(since 2020)

36

Email

University Profile Page

Indiana University Bloomington

Google Scholar

View Google Scholar Profile

David Leake Skills & Research Interests

Case-Based Reasoning

Cognitive Science

Explanation

Intelligent User Interfaces

Neuro-Symbolic AI

Top articles of David Leake

Title

Journal

Author(s)

Publication Date

Bridging AI Paradigms with Cases and Networks

Computer Sciences & Mathematics Forum

David Leake

2023/8/14

Towards Addressing Problem-Distribution Drift with Case Discovery

Case-based Reasoning Research and Development: 31st International Conference, ICCBR 2023, Aberdeen, UK, July 17-20, 2023, Proceedings

David Leake

Brian Schack

2023

Enhancing Case-Based Reasoning with Neural Networks

Compendium of Neurosymbolic Artificial Intelligence

David Leake

Zachary Wilkerson

Xiaomeng Ye

David J Crandall

2023/8/4

Examining the Impact of Network Architecture on Extracted Feature Quality for CBR

David Leake

Zachary Wilkerson

Vibhas Vats

Karan Acharya

David Crandall

2023/7/17

Less is Better: An Energy-Based Approach to Case Base Competence

Esteban Marquer

Fadi Badra

Marie-Jeanne Lesot

Miguel Couceiro

David Leake

2023/7/17

Combining Case-Based Reasoning with Deep Learning: Context and Ongoing Case Feature Learning Research

David Leake

Zachary Wilkerson

David J Crandall

2023/12/11

Large language models need symbolic AI

Proceedings of the 17th International Workshop on Neural-Symbolic Learning and Reasoning, La Certosa di Pontignano, Siena, Italy

Kristian Hammond

David Leake

2023/7/3

In Memoriam: Roger C. Schank, 1946–2023

AI Magazine

Richard Granger

David Leake

Christopher K Riesbeck

2023/10/1

Cases are King: A User Study of Case Presentation to Explain CBR Decisions

Lawrence Gates

David Leake

Kaitlynne Wilkerson

2023/7

Leveraging SHAP and CBR for Dimensionaltiy Reduction on the Psychology Prediction Dataset.

Zachary Wilkerson

David Leake

David Crandall

2022

Generation and Evaluation of Creative Images from Limited Data: A Class-to-Class VAE Approach.

Xiaomeng Ye

Ziwei Zhao

David Leake

David Crandall

2022

Extracting case indices from convolutional neural networks: A comparative study

David Leake

Zachary Wilkerson

David Crandall

2022/8/14

Case adaptation with neural networks: Capabilities and limitations

Xiaomeng Ye

David Leake

David Crandall

2022/8/14

Case-based Explanation: Making the Implicit Explicit.

David Leake

2022

Generating Counterfactual Images: Towards a C2C-VAE Approach.

Ziwei Zhao

David Leake

Xiaomeng Ye

David J Crandall

2022

On combining knowledge-engineered and network-extracted features for retrieval

Zachary Wilkerson

David Leake

David J Crandall

2021

Harmonizing case retrieval and adaptation with alternating optimization

David Leake

Xiaomeng Ye

2021

Learning adaptations for case-based classification: A neural network approach

Xiaomeng Ye

David Leake

Vahid Jalali

David J Crandall

2021

Applying the case difference heuristic to learn adaptations from deep network features

arXiv preprint arXiv:2107.07095

Xiaomeng Ye

Ziwei Zhao

David Leake

Xizi Wang

David Crandall

2021/7/15

Supporting Case-Based Reasoning with Neural Networks: An Illustration for Case Adaptation.

AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering

David Leake

Xiaomeng Ye

David J Crandall

2021/3/22

See List of Professors in David Leake University(Indiana University Bloomington)

Co-Authors

H-index: 84
Barry Smyth

Barry Smyth

University College Dublin

H-index: 64
Kenneth D. Forbus

Kenneth D. Forbus

Northwestern University

H-index: 60
Mary Lou Maher

Mary Lou Maher

University of North Carolina at Charlotte

H-index: 55
Kristian Hammond

Kristian Hammond

North Western University

academic-engine