Search Results for author: Joseph Wang

Found 14 papers, 1 papers with code

Wakeword Detection under Distribution Shifts

no code implementations13 Jul 2022 Sree Hari Krishnan Parthasarathi, Lu Zeng, Christin Jose, Joseph Wang

To train effectively with a mix of human and teacher labeled data, we develop a teacher labeling strategy based on confidence heuristics to reduce entropy on the label distribution from the teacher model; the data is then sampled to match the marginal distribution on the labels.

Keyword Spotting

Latency Control for Keyword Spotting

no code implementations15 Jun 2022 Christin Jose, Joseph Wang, Grant P. Strimel, Mohammad Omar Khursheed, Yuriy Mishchenko, Brian Kulis

We also show that when our approach is used in conjunction with a max-pooling loss, we are able to improve relative false accepts by 25 % at a fixed latency when compared to cross entropy loss.

Keyword Spotting

Self-Healing Small-Scale Swimmers

no code implementations7 Dec 2020 Emil Karshalev, Cristian Silva-Lopez, Kyle Chan, Jieming Yan, Elodie Sandraz, Mathieu Gallot, Amir Nourhani, Javier Garay, Joseph Wang

Herein, self-healing small-scale swimmers capable of autonomous propulsion and on-the-fly structural recovery are described.

Soft Condensed Matter Materials Science

Probabilistic Semantic Retrieval for Surveillance Videos with Activity Graphs

no code implementations17 Dec 2017 Yu-Ting Chen, Joseph Wang, Yannan Bai, Gregory Castañón, Venkatesh Saligrama

We present a novel framework for finding complex activities matching user-described queries in cluttered surveillance videos.

Retrieval Semantic Retrieval

Field of Groves: An Energy-Efficient Random Forest

no code implementations10 Apr 2017 Zafar Takhirov, Joseph Wang, Marcia S. Louis, Venkatesh Saligrama, Ajay Joshi

In this work, we present a field of groves (FoG) implementation of random forests (RF) that achieves an accuracy comparable to CNNs and SVMs under tight energy budgets.

General Classification

Adaptive Neural Networks for Efficient Inference

2 code implementations ICML 2017 Tolga Bolukbasi, Joseph Wang, Ofer Dekel, Venkatesh Saligrama

We first pose an adaptive network evaluation scheme, where we learn a system to adaptively choose the components of a deep network to be evaluated for each example.

Binary Classification

Efficient Learning by Directed Acyclic Graph For Resource Constrained Prediction

no code implementations NeurIPS 2015 Joseph Wang, Kirill Trapeznikov, Venkatesh Saligrama

We learn node policies in the DAG by reducing the global objective to a series of cost sensitive learning problems.

Sensor Selection by Linear Programming

no code implementations9 Sep 2015 Joseph Wang, Kirill Trapeznikov, Venkatesh Saligrama

We decompose the problem, which is known to be intractable, into combinatorial (tree structures) and continuous parts (node decision rules) and propose to solve them separately.

Computational Efficiency

Feature-Budgeted Random Forest

no code implementations20 Feb 2015 Feng Nan, Joseph Wang, Venkatesh Saligrama

We seek decision rules for prediction-time cost reduction, where complete data is available for training, but during prediction-time, each feature can only be acquired for an additional cost.

Max-Cost Discrete Function Evaluation Problem under a Budget

no code implementations12 Jan 2015 Feng Nan, Joseph Wang, Venkatesh Saligrama

We develop a broad class of \emph{admissible} impurity functions that admit monomials, classes of polynomials, and hinge-loss functions that allow for flexible impurity design with provably optimal approximation bounds.

General Classification

Local Supervised Learning through Space Partitioning

no code implementations NeurIPS 2012 Joseph Wang, Venkatesh Saligrama

We show that space partitioning can be equivalently reformulated as a supervised learning problem and consequently any discriminative learning method can be utilized in conjunction with our approach.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.