Papers

Kan Extensions in Data Science and Machine Learning . Shiebler, D. (TBD))

Generalized Optimization: A First Step Towards Category Theoretic Learning Theory. Shiebler, D. Advances in Intelligent Systems and Computing (2021)

Functorial Manifold Learning. Shiebler, D. Applied Category Theory (2021)

Category Theory in Machine Learning. Shiebler, D., Gavranović, B., & Wilson, P. Applied Category Theory (2021)

Flattening Multiparameter Hierarchical Clustering Functors. Shiebler, D. Geometric Science of Information (2021)

Functorial Clustering via Simplicial Complexes. Shiebler, D. NeurIPS Workshop on Topological Data Analysis (2020)

Categorical Stochastic Processes and Likelihood. Shiebler, D. Applied Category Theory (2020)

Tuning Word2vec for Large Scale Recommendation Systems. Chamberlain, B., Rossi, E., Shiebler, D., Sedhain, S., Bronstein, M. RecSys (2020)

Lessons Learned Addressing Dataset Bias in Model-Based Candidate Generation at Twitter. Virani, A., Baxter, J., Shiebler, D., Gautier, P., Verma, S., Xia, Y., Sharma, A., Binnani, S., Chen, L., Yu, C. KDD Workshop on Industrial Recommendation Systems (2020)

Developments in AI and Machine Learning for Neuroimaging. O’Sullivan, S., Jean-Quartier, F., Jean-Quartier, C., Holzinger, A., Shiebler, D., Moon, P., Angione, C. Artificial Intelligence and Machine Learning for Digital Pathology - LNCS 12090 (2020)

Incremental Monoidal Grammars. Shiebler, D., Toumi, A., Sadrzadeh, M. SYCO (2019)

Learning what and where to attend with humans in the loop. Linsley, D., Shiebler, D., Eberhardt, S., & Serre, T. ICLR (2018)

A Correlation Maximization Approach for Cross Domain Co-Embeddings. Shiebler, D. arVix (2018)

Global-and-local attention networks for visual recognition. Linsley, D., Shiebler, D., Eberhardt, S., & Serre, T. Computational Cognitive Neuroscience (2018)

Fighting Redundancy and Model Decay with Embeddings. Shiebler, D., Belli, L., Baxter, J., Xiong, H., & Tayal, A. KDD Workshop on Common Model Infrastructure (2018)

Making Machine Learning Easy with Embeddings. Shiebler, D., & Tayal, A. MLSys, formally SysML (2018)

A Dichotomy of Visual Relations. Kim, J., Ricci, M., Shiebler, D., & Serre, T. Computational Cognitive Neuroscience (2017)

Beta Shift and Decision Conflict. Shiebler, D. Brown University Neuroscience Sc.B Honors Thesis (2015)

Patents

Systems and Methods for Detecting and Assessing Distracted Drivers. Cordova, B., Finegold, R., Shiebler, D., & Farrell, K. (U.S. 2017/0105098 A1)

Systems and Methods for Scoring Driver Trips Cordova, B., Finegold, R., Shiebler, D., & Cecala, S. (U.S. 2017/0349182 A1)

Systems and Methods for Sensor-Based Vehicle Crash Prediction, Detection and Reconstruction. Cordova, B., Vaisman, E., & Shiebler, D. (U.S. 2017/0210323 A1)

Systems and Methods for Detecting Airbag Deployment Resulting From a Vehicle Crash Cordova, B., Vaisman, E., & Shiebler, D. (U.S. 2018/0126938 A1)

Conference Abstracts

A Coalgebraic 2-Categorical Model for Dynamic Syntax. Shiebler, D., Toumi, A., Sadrzadeh, M. Dynamic Syntax (2020)

Capturing Lingual Shifts in Word Embeddings with CCA. Kamani, M., Shiebler, D., Tayal, A., Verma, S., & Belli, L. WeCNLP (2018)

FastTweets: Measuring Embedding Quality for Highly Variable Text Data. Rabhi, S., Green, C., Verma, S., Shiebler, D., & Belli, L. WeCNLP (2018)

A Data-Driven Approach to Learning 3D Shape. Eberhardt, S., Shiebler, D., Linsley, D., & Serre, T. Journal of Vision. (2017)

Large-scale discovery of visual features for object recognition. Linsley, D., Eberhardt, S., Shiebler, D., & Serre, T. Computational and Mathematical Models in Vision (2017)

More Feedback, Less Depth: Approximating Human Vision with Deep Networks. Eberhardt, S., Cader, J., Linsley, D., Barhomi, Y., Shiebler, D., & Serre, T. NIPS Workshop on Representation Learning in Artificial and Biological Neural Networks (2016)