Research publications

Please see my Google Scholar and arXiv profiles for my research papers, which range from AI/ML to neuroscience.

Main

Recursive Cortical Network

  • George, Lavin, et al. A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs. Science 2017. /// paper, blog, code

  • George, Lavin, et al. Cortical Microcircuits from a Generative Vision Model. CCN 2018. /// paper

Hierarchical Temporal Memory

  • Ahmad, Lavin, et al. Unsupervised real-time anomaly detection for streaming data. Neurocomputing 2017. /// paper, code

  • Hawkins, Lavin, et al. Biological and Machine Intelligence. 2016. /// book

Data-efficient computer vision

  • Naud & Lavin (2020), Manifolds for Unsupervised Visual Anomaly Detection. /// paper

  • Haney & Lavin. Fine-Grain Few-Shot Vision via Domain Knowledge as Hyperspherical Priors. CVPR Fine-grain Vision Workshop 2020. /// paper, video

Recent in-press

  • Lavin (2020), Neuro-symbolic Neurodegenerative Disease Modeling as Probabilistic Programmed Deep Kernels. /// paper

  • Lavin (2020), Probabilistic Programmed Causal Inference.

  • Lavin & Renard. Technology Readiness Levels for Machine Learning Systems. ICML 2020 Workshop on Challenges in Deploying ML Systems. /// paper

  • Lippoldt & Lavin. Attention-Sampling Graph Convolutional Networks. 2020 BayLearn Symposium.

  • Haney & Lavin (2020). Probabilistic Domain-Expert Hyperspherical Networks.

  • Lavin (2020), Accelerating Gaussian Processes and Deep Kernel Networks on GPUs. /// video

  • Lavin (2019), Predictive Modeling Neurodegenerative Processes with a Domain-Specific Probabilistic Programming Language.

  • Lavin. Integration of human-like covert-overt attention with probabilistic neural networks. Neuroscience to Artificially Intelligent Systems (NAISys) 2020. /// abs


AI & innovation articles

I contribute articles to Forbes on AI & ML, discussing important intersections with these technologies and society.

  • “Doing The Hard Things: AI, Space, and Climate Science”

    This is not a time for an international arms race in AI. Rather, it is a time for collaboration across governments, corporate R&D, academia, and startups. It is a time to push the frontier of AI and space for climate science and humankind.

forbes cover


And speaking…

On brains n bits, AI, and SW. For example,

TEDX talk