Výsledky vyhledávání - "Tida, Vijay Srinivas"

Report

Facebook Report on Privacy of fNIRS data

Autor: Hossen, Md Imran, Chilukoti, Sai Venkatesh, Shan, Liqun, Tida, Vijay Srinivas, Hei, Xiali

The primary goal of this project is to develop privacy-preserving machine learning model training techniques for fNIRS data. This project will build a local model in a centralized setting with both differential privacy (DP) and certified robustness.

Externí odkaz: http://arxiv.org/abs/2401.00973

Zobrazit plný text záznamu

Report

Auto DP-SGD: Dual Improvements of Privacy and Accuracy via Automatic Clipping Threshold and Noise Multiplier Estimation

Autor: Chilukoti, Sai Venkatesh, Hossen, Md Imran, Shan, Liqun, Tida, Vijay Srinivas, Hei, Xiai

DP-SGD has emerged as a popular method to protect personally identifiable information in deep learning applications. Unfortunately, DP-SGD's per-sample gradient clipping and uniform noise addition during training can significantly degrade model utili

Externí odkaz: http://arxiv.org/abs/2312.02400

Zobrazit plný text záznamu

Report

Kernel-Segregated Transpose Convolution Operation

Autor: Tida, Vijay Srinivas, Chilukoti, Sai Venkatesh, Hei, Xiali, Hsu, Sonya

Transpose convolution has shown prominence in many deep learning applications. However, transpose convolution layers are computationally intensive due to the increased feature map size due to adding zeros after each element in each row and column. Th

Externí odkaz: http://arxiv.org/abs/2209.03704

Zobrazit plný text záznamu

Report

Universal Spam Detection using Transfer Learning of BERT Model

Autor: Tida, Vijay Srinivas, Hsu, Sonya

Deep learning transformer models become important by training on text data based on self-attention mechanisms. This manuscript demonstrated a novel universal spam detection model using pre-trained Google's Bidirectional Encoder Representations from T

Externí odkaz: http://arxiv.org/abs/2202.03480

Zobrazit plný text záznamu