Filter Results:
(46)
Show Results For
- All HBS Web (46)
- Faculty Publications (25)
Show Results For
- All HBS Web (46)
- Faculty Publications (25)
Page 1 of 46
Results →
- 2022
- Article
Efficiently Training Low-Curvature Neural Networks
By: Suraj Srinivas, Kyle Matoba, Himabindu Lakkaraju and Francois Fleuret
Standard deep neural networks often have excess non-linearity, making them susceptible to issues such as low adversarial robustness and gradient instability. Common methods to address these downstream issues, such as adversarial training, are expensive and often... View Details
Keywords: AI and Machine Learning
Srinivas, Suraj, Kyle Matoba, Himabindu Lakkaraju, and Francois Fleuret. "Efficiently Training Low-Curvature Neural Networks." Advances in Neural Information Processing Systems (NeurIPS) (2022).
- 2023
- Article
Evaluating Explainability for Graph Neural Networks
By: Chirag Agarwal, Owen Queen, Himabindu Lakkaraju and Marinka Zitnik
As explanations are increasingly used to understand the behavior of graph neural networks (GNNs), evaluating the quality and reliability of GNN explanations is crucial. However, assessing the quality of GNN explanations is challenging as existing graph datasets have no... View Details
Keywords: Analytics and Data Science
Agarwal, Chirag, Owen Queen, Himabindu Lakkaraju, and Marinka Zitnik. "Evaluating Explainability for Graph Neural Networks." Art. 114. Scientific Data 10 (2023).
- Article
Incorporating Interpretable Output Constraints in Bayesian Neural Networks
By: Wanqian Yang, Lars Lorch, Moritz Graule, Himabindu Lakkaraju and Finale Doshi-Velez
Domains where supervised models are deployed often come with task-specific constraints, such as prior expert knowledge on the ground-truth function, or desiderata like safety and fairness. We introduce a novel probabilistic framework for reasoning with such constraints... View Details
Yang, Wanqian, Lars Lorch, Moritz Graule, Himabindu Lakkaraju, and Finale Doshi-Velez. "Incorporating Interpretable Output Constraints in Bayesian Neural Networks." Advances in Neural Information Processing Systems (NeurIPS) 33 (2020).
- 2021
- Chapter
Towards a Unified Framework for Fair and Stable Graph Representation Learning
By: Chirag Agarwal, Himabindu Lakkaraju and Marinka Zitnik
As the representations output by Graph Neural Networks (GNNs) are increasingly employed in real-world applications, it becomes important to ensure that these representations are fair and stable. In this work, we establish a key connection between counterfactual... View Details
Agarwal, Chirag, Himabindu Lakkaraju, and Marinka Zitnik. "Towards a Unified Framework for Fair and Stable Graph Representation Learning." In Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence, edited by Cassio de Campos and Marloes H. Maathuis, 2114–2124. AUAI Press, 2021.
- Article
Timing in the Absence of Clocks: Encoding Time in Neural Network States
By: Uma R. Karmarkar and Dean V. Buonomano
Karmarkar, Uma R., and Dean V. Buonomano. "Timing in the Absence of Clocks: Encoding Time in Neural Network States." Neuron 53, no. 3 (February 2007): 427–38.
- 2022
- Article
Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods.
By: Chirag Agarwal, Marinka Zitnik and Himabindu Lakkaraju
As Graph Neural Networks (GNNs) are increasingly employed in real-world applications, it becomes critical to ensure that the stakeholders understand the rationale behind their predictions. While several GNN explanation methods have been proposed recently, there has... View Details
Keywords: Graph Neural Networks; Explanation Methods; Mathematical Methods; Framework; Theory; Analysis
Agarwal, Chirag, Marinka Zitnik, and Himabindu Lakkaraju. "Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods." Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS) 25th (2022).
- December 2018
- Case
Choosy
By: Jeffrey J. Bussgang and Julia Kelley
Founded in 2017, Choosy is a data-driven fashion startup that uses algorithms to identify styles trending on social media. After manufacturing similar items using a China-based supply chain, Choosy sells them to consumers through its website and social media pages.... View Details
Keywords: Artificial Intelligence; Algorithms; Machine Learning; Neural Networks; Instagram; Influencer; Fast Fashion; Design; Customer Satisfaction; Customer Focus and Relationships; Decision Making; Cost vs Benefits; Innovation and Invention; Brands and Branding; Product Positioning; Demand and Consumers; Supply Chain; Production; Logistics; Business Model; Expansion; Internet and the Web; Mobile and Wireless Technology; Digital Platforms; Social Media; Technology Industry; Fashion Industry; North and Central America; United States; New York (state, US); New York (city, NY)
- November 2024
- Supplement
AlphaGo (C): Birth of a New Intelligence
By: Shikhar Ghosh and Shweta Bagai
This case, the final of a three-part series, explores DeepMind's pivotal transition from mastering games to solving real-world scientific challenges. In December 2020, DeepMind's AI system AlphaFold 2 achieved a breakthrough by solving protein folding—a 50-year-old... View Details
Keywords: Autonomy; Deep Learning; Drug Discovery; Healthcare Innovation; Neural Networks; Scientific Research; Technology Startup; AI and Machine Learning; Technological Innovation; Research and Development; Business Model; Business Strategy; Open Source Distribution; Technology Industry; United States
Ghosh, Shikhar, and Shweta Bagai. "AlphaGo (C): Birth of a New Intelligence." Harvard Business School Supplement 825-075, November 2024.
- 2020
- Working Paper
Machine Learning for Pattern Discovery in Management Research
Supervised machine learning (ML) methods are a powerful toolkit for discovering robust patterns in quantitative data. The patterns identified by ML could be used as an observation for further inductive or abductive research, but should not be treated as the result of a... View Details
Keywords: Machine Learning; Theory Building; Induction; Decision Trees; Random Forests; K-nearest Neighbors; Neural Network; P-hacking; Analytics and Data Science; Analysis
Choudhury, Prithwiraj, Ryan Allen, and Michael G. Endres. "Machine Learning for Pattern Discovery in Management Research." Harvard Business School Working Paper, No. 19-032, September 2018. (Revised June 2020.)
- January 2021
- Article
Machine Learning for Pattern Discovery in Management Research
By: Prithwiraj Choudhury, Ryan Allen and Michael G. Endres
Supervised machine learning (ML) methods are a powerful toolkit for discovering robust patterns in quantitative data. The patterns identified by ML could be used for exploratory inductive or abductive research, or for post-hoc analysis of regression results to detect... View Details
Keywords: Machine Learning; Supervised Machine Learning; Induction; Abduction; Exploratory Data Analysis; Pattern Discovery; Decision Trees; Random Forests; Neural Networks; ROC Curve; Confusion Matrix; Partial Dependence Plots; AI and Machine Learning
Choudhury, Prithwiraj, Ryan Allen, and Michael G. Endres. "Machine Learning for Pattern Discovery in Management Research." Strategic Management Journal 42, no. 1 (January 2021): 30–57.
- Article
Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error
By: Celia Cintas, Skyler Speakman, Victor Akinwande, William Ogallo, Komminist Weldemariam, Srihari Sridharan and Edward McFowland III
Reliably detecting attacks in a given set of inputs is of high practical relevance because of the vulnerability of neural networks to adversarial examples. These altered inputs create a security risk in applications with real-world consequences, such as self-driving... View Details
Keywords: Autoencoder Networks; Pattern Detection; Subset Scanning; Computer Vision; Statistical Methods And Machine Learning; Machine Learning; Deep Learning; Data Mining; Big Data; Large-scale Systems; Mathematical Methods; Analytics and Data Science
Cintas, Celia, Skyler Speakman, Victor Akinwande, William Ogallo, Komminist Weldemariam, Srihari Sridharan, and Edward McFowland III. "Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error." Proceedings of the International Joint Conference on Artificial Intelligence 29th (2020).
- July 2024
- Technical Note
What Is AI?
By: Michael Parzen and Jo Ellery
This note discusses definitions of artificial intelligence and covers the broad types of learning used in training AI, as well as explaining in detail how neural networks are built, trained, and used. View Details
Keywords: AI and Machine Learning
Parzen, Michael, and Jo Ellery. "What Is AI?" Harvard Business School Technical Note 625-010, July 2024.
- 2021
- Working Paper
Deep Learning for Two-Sided Matching
By: Sai Srivatsa Ravindranatha, Zhe Feng, Shira Li, Jonathan Ma, Scott Duke Kominers and David Parkes
We initiate the use of a multi-layer neural network to model two-sided matching and to explore the design space between strategy-proofness and stability. It is well known that both properties cannot be achieved simultaneously but the efficient frontier in this design... View Details
Keywords: Strategy-proofness; Deep Learning; Two-Sided Platforms; Marketplace Matching; Balance and Stability
Srivatsa Ravindranatha, Sai, Zhe Feng, Shira Li, Jonathan Ma, Scott Duke Kominers, and David Parkes. "Deep Learning for Two-Sided Matching." Working Paper, July 2021.
- 2018
- Working Paper
Some Facts of High-Tech Patenting
By: Michael Webb, Nick Short, Nicholas Bloom and Josh Lerner
Patenting in software, cloud computing, and artificial intelligence has grown rapidly in recent years. Such patents are acquired primarily by large U.S. technology firms such as IBM, Microsoft, Google, and HP, as well as by Japanese multinationals such as Sony, Canon,... View Details
Webb, Michael, Nick Short, Nicholas Bloom, and Josh Lerner. "Some Facts of High-Tech Patenting." Harvard Business School Working Paper, No. 19-014, August 2018. (NBER Working Paper Series, No. 24793, July 2018.)
- 2023
- Article
M4: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities, and Models
By: Himabindu Lakkaraju, Xuhong Li, Mengnan Du, Jiamin Chen, Yekun Chai and Haoyi Xiong
While Explainable Artificial Intelligence (XAI) techniques have been widely studied to explain predictions made by deep neural networks, the way to evaluate the faithfulness of explanation results remains challenging, due to the heterogeneity of explanations for... View Details
Keywords: AI and Machine Learning
Lakkaraju, Himabindu, Xuhong Li, Mengnan Du, Jiamin Chen, Yekun Chai, and Haoyi Xiong. "M4: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities, and Models." Advances in Neural Information Processing Systems (NeurIPS) (2023).
- 2021
- Working Paper
First Law of Motion: Influencer Video Advertising on TikTok
By: Jeremy Yang, Juanjuan Zhang and Yuhan Zhang
This paper engineers an intuitive feature that is predictive of the causal effect of influencer video advertising on product sales. We propose the concept of m-score, a summary statistic that captures the extent to which a product is advertised in the most engaging... View Details
Keywords: Influencer Advertising; Video Advertising; Computer Vision; Machine Learning; Advertising; Online Technology
Yang, Jeremy, Juanjuan Zhang, and Yuhan Zhang. "First Law of Motion: Influencer Video Advertising on TikTok." Working Paper, March 2021.
- 2009
- Case
The Prediction Lover's Handbook
By: Thomas H. Davenport and Jeanne G. Harris
When picking assessment tools to inform better decisions about future paths, executives are faced with a wide variety of options--some of which are well established, while others are in early stages of development. The authors provide an insider's guide to prediction... View Details
Davenport, Thomas H., and Jeanne G. Harris. "The Prediction Lover's Handbook." 2009.
- 2019
- Working Paper
Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles
By: Prithwiraj Choudhury, Dan Wang, Natalie A. Carlson and Tarun Khanna
We demonstrate how a novel synthesis of three methods—(1) unsupervised topic modeling of text data to generate new measures of textual variance, (2) sentiment analysis of text data, and (3) supervised ML coding of facial images with a cutting-edge convolutional neural... View Details
Choudhury, Prithwiraj, Dan Wang, Natalie A. Carlson, and Tarun Khanna. "Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles." Harvard Business School Working Paper, No. 18-064, January 2018. (Revised May 2019.)
- September 2023 (Revised April 2024)
- Case
Atomwise: Strategic Opportunities in AI for Pharma
By: Satish Tadikonda
Abraham Heifets and his co-founder, Izhar Wallach, had founded Atomwise to develop i) an AI engine to transform drug discovery by creating better medicines faster, and ii) a machine learning-based discovery engine that combined the power of convolutional neural... View Details
Keywords: Business Model; Business Startups; AI and Machine Learning; Science-Based Business; Technological Innovation; Biotechnology Industry; Pharmaceutical Industry
Tadikonda, Satish. "Atomwise: Strategic Opportunities in AI for Pharma." Harvard Business School Case 824-043, September 2023. (Revised April 2024.)
- Article
Pattern Detection in the Activation Space for Identifying Synthesized Content
By: Celia Cintas, Skyler Speakman, Girmaw Abebe Tadesse, Victor Akinwande, Edward McFowland III and Komminist Weldemariam
Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise. The ability to synthesize high-quality content at a large scale brings potential risks as the generated samples may... View Details
Cintas, Celia, Skyler Speakman, Girmaw Abebe Tadesse, Victor Akinwande, Edward McFowland III, and Komminist Weldemariam. "Pattern Detection in the Activation Space for Identifying Synthesized Content." Pattern Recognition Letters 153 (January 2022): 207–213.