Jiaqi Liu

Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition

2016 · arXiv (Cornell University)

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network. Especially, …

HeteFed: Heterogeneous Federated Learning with Privacy-Preserving Binary Low-Rank Matrix Decomposition Method

2023

Federated learning is a machine learning paradigm where many clients collaboratively train a machine learning model while ensuring the nondisclosure of local data sets. Existing federated learning methods conduct optimization over the same model structure, …

Prediction of Wordle player data based on BP neural network optimized by genetic algorithm

2023

This article mainly uses the data provided by Wordle player to predict the distribution of score results for a certain word in the future. However, the scoring results have high uncertainty. There are many evaluation …

Does Bigger Mean Better? Comparitive Analysis of CNNs and Biomedical Vision Language Modles in Medical Diagnosis

2025 · arXiv (Cornell University)

The accurate interpretation of chest radiographs using automated methods is a critical task in medical imaging. This paper presents a comparative analysis between a supervised lightweight Convolutional Neural Network (CNN) and a state-of-the-art, zero-shot medical …