Search Results for author: Ting Hu

Found 12 papers, 0 papers with code

Scaled Prompt-Tuning for Few-Shot Natural Language Generation

no code implementations13 Sep 2023 Ting Hu, Christoph Meinel, Haojin Yang

The increasingly Large Language Models (LLMs) demonstrate stronger language understanding and generation capabilities, while the memory demand and computation cost of fine-tuning LLMs on downstream tasks are non-negligible.

Text Generation

Genetic heterogeneity analysis using genetic algorithm and network science

no code implementations12 Aug 2023 Zhendong Sha, Yuanzhu Chen, Ting Hu

Through genome-wide association studies (GWAS), disease susceptible genetic variables can be identified by comparing the genetic data of individuals with and without a specific disease.

feature selection

Evolutionary approaches to explainable machine learning

no code implementations23 Jun 2023 Ryan Zhou, Ting Hu

We then focus on how evolutionary computing can be used in XAI/XML, and review some approaches which incorporate EC techniques.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

Phenotype Search Trajectory Networks for Linear Genetic Programming

no code implementations15 Nov 2022 Ting Hu, Gabriela Ochoa, Wolfgang Banzhaf

Genotype-to-phenotype mappings translate genotypic variations such as mutations into phenotypic changes.

Empirical Evaluation of Post-Training Quantization Methods for Language Tasks

no code implementations29 Oct 2022 Ting Hu, Christoph Meinel, Haojin Yang

We further explore the limit of quantization bit and show that OCS could quantize BERT-Base and BERT-Large to 3-bits and retain 98% and 96% of the performance on the GLUE benchmark accordingly.

Quantization Reading Comprehension

A spectral-spatial fusion anomaly detection method for hyperspectral imagery

no code implementations24 Feb 2022 Zengfu Hou, Siyuan Cheng, Ting Hu

In hyperspectral, high-quality spectral signals convey subtle spectral differences to distinguish similar materials, thereby providing unique advantage for anomaly detection.

Anomaly Detection

DiriNet: A network to estimate the spatial and spectral degradation functions

no code implementations27 Jan 2022 Ting Hu

To learn the spatial response function and the point spread function from the image pairs to be fused, we propose a Dirichlet network, where both functions are properly constrained.

A Permutation-Invariant Representation of Neural Networks with Neuron Embeddings

no code implementations29 Sep 2021 Ryan Zhou, Christian Muise, Ting Hu

A key property of this representation is that there are multiple representations of a network which can be obtained by permuting the order of the neurons.

Transfer Learning

Stochastic Gradient Descent for Nonconvex Learning without Bounded Gradient Assumptions

no code implementations3 Feb 2019 Yunwen Lei, Ting Hu, Guiying Li, Ke Tang

While the behavior of SGD is well understood in the convex learning setting, the existing theoretical results for SGD applied to nonconvex objective functions are far from mature.

Consistency Analysis of an Empirical Minimum Error Entropy Algorithm

no code implementations17 Dec 2014 Jun Fan, Ting Hu, Qiang Wu, Ding-Xuan Zhou

The error entropy consistency, which requires the error entropy of the learned function to approximate the minimum error entropy, is shown to be always true if the bandwidth parameter tends to 0 at an appropriate rate.


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