Home /
Research
Showing 613 - 618 / 897
Towards NNGP-guided Neural Architecture Search
DanielS.Park, JaehoonLee, DaiyiPeng....
Published date-11/11/2020
NeuralArchitectureSearch
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
LucasRosenblatt, XiaoyanLiu, SamiraPouyanfar....
Published date-11/11/2020
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
MohsenJafarzadeh, TouqeerAhmad, AkshayRajDhamija....
Published date-11/11/2020
ImageClassification
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
ShangJiang, HaoranQin, BingliZhang....
Published date-11/11/2020
ObjectDetection
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
HuahuanZheng, KeyuAn, ZhijianOu....
Published date-11/11/2020
End-To-EndSpeechRecognition, GraphSampling, NeuralArchitectureSearch, SpeechRecognition
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
JayarajPoroor....
Published date-11/10/2020
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 …