Home /

Research

Showing 613 - 618 / 897

Towards NNGP-guided Neural Architecture Search


Authors:  DanielS.Park, JaehoonLee, DaiyiPeng....
Published date-11/11/2020
Tasks:  NeuralArchitectureSearch

Abstract: The predictions of wide Bayesian neural networks are described by a Gaussian process, known as the Neural Network Gaussian Process (NNGP). Analytic forms for NNGP kernels are known for many …

Differentially Private Synthetic Data: Applied Evaluations and Enhancements


Authors:  LucasRosenblatt, XiaoyanLiu, SamiraPouyanfar....
Published date-11/11/2020

Abstract: Machine learning practitioners frequently seek to leverage the most informative available data, without violating the data owner's privacy, when building predictive models. Differentially private data synthesis protects personal details from …

Automatic Open-World Reliability Assessment


Authors:  MohsenJafarzadeh, TouqeerAhmad, AkshayRajDhamija....
Published date-11/11/2020
Tasks:  ImageClassification

Abstract: Image classification in the open-world must handle out-of-distribution (OOD) images. Systems should ideally reject OOD images, or they will map atop of known classes and reduce reliability. Using open-set classifiers …

Optimized Loss Functions for Object detection: A Case Study on Nighttime Vehicle Detection


Authors:  ShangJiang, HaoranQin, BingliZhang....
Published date-11/11/2020
Tasks:  ObjectDetection

Abstract: Loss functions is a crucial factor that affecting the detection precision in object detection task. In this paper, we optimize both two loss functions for classification and localization simultaneously. Firstly, …

Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients


Authors:  HuahuanZheng, KeyuAn, ZhijianOu....
Published date-11/11/2020
Tasks:  End-To-EndSpeechRecognition, GraphSampling, NeuralArchitectureSearch, SpeechRecognition

Abstract: Neural Architecture Search (NAS), the process of automating architecture engineering, is an appealing next step to advancing end-to-end Automatic Speech Recognition (ASR), replacing expert-designed networks with learned, task-specific architectures. In …

MotePy: A domain specific language for low-overhead machine learning and data processing


Authors:  JayarajPoroor....
Published date-11/10/2020

Abstract: A domain specific language (DSL), named MotePy is presented. The DSL offers a high level syntax with low overheads for ML/data processing in time constrained or memory constrained systems. The …

Filter by

Categories

Tags