2.2k citations
- IBM (United States)US73 papers
- Stanford UniversityUS62 papers
- IBM Research - Thomas J. Watson Research CenterUS42 papers
- University of California, BerkeleyUS22 papers
- IBM Research - ZurichCH21 papers
- California Institute of TechnologyUS20 papers
- École Polytechnique Fédérale de LausanneCH15 papers
- Massachusetts Institute of TechnologyUS14 papers
- Max Planck Institute of Microstructure PhysicsDE13 papers
- ETH ZurichCH10 papers
- Princeton UniversityUS10 papers
- SLAC National Accelerator LaboratoryUS10 papers
25 papers · 1 filter
Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification
Marc Combalia, Veronica Vilaplana
We propose a patch sampling strategy based on a sequential Monte-Carlo method for high resolution image classification in the context of Multiple Instance Learning. When compared w…
Minimal Effective Gibbs Ansatz (MEGA): A simple protocol for extracting an accurate thermal representation for quantum simulation
Jeffrey Cohn, Khadijeh Sona Najafi, Forest Yang +2
Quantum Gibbs state sampling algorithms generally suffer from either scaling exponentially with system size or requiring specific knowledge of spectral properties \textit{a priori}…
A Hybrid Approach to Privacy-Preserving Federated Learning
Stacey Truex, Nathalie Baracaldo, Ali Anwar +4
Federated learning facilitates the collaborative training of models without the sharing of raw data. However, recent attacks demonstrate that simply maintaining data locality durin…
Towards Instance-Optimal Private Query Release
Jaroslaw Blasiok, Mark Bun, Aleksandar Nikolov +1
We study efficient mechanisms for the query release problem in differential privacy: given a workload of statistical queries, output approximate answers to the queries while sa…
Challenge AI Mind: A Crowd System for Proactive AI Testing
Siwei Fu, Anbang Xu, Xiaotong Liu +2
Artificial Intelligence (AI) has burrowed into our lives in various aspects; however, without appropriate testing, deployed AI systems are often being criticized to fail in critica…
Using Multi-task and Transfer Learning to Solve Working Memory Tasks
T. S. Jayram, Tomasz Kornuta, Ryan L. McAvoy +1
We propose a new architecture called Memory-Augmented Encoder-Solver (MAES) that enables transfer learning to solve complex working memory tasks adapted from cognitive psychology.…