Search Results for author:
Found 11 papers, 3 papers with code
Effects of Different Prompts on the Quality of GPT-4 Responses to Dementia Care Questions
Evidence suggests that different prompts lead large language models (LLMs) to generate responses with varying quality.
ReCoMIF: Reading comprehension based multi-source information fusion network for Chinese spoken language understanding
It usually includes slot filling and intent detection (SFID) tasks aiming at semantic parsing of utterances.
Chiral Decomposition of Twisted Graphene Multilayers with Arbitrary Stacking
We formulate the chiral decomposition rules that govern the electronic structure of a broad family of twisted $N+M$ multilayer graphene configurations that combine arbitrary stacking order and a mutual twist.
Mesoscale and Nanoscale Physics Materials Science Strongly Correlated Electrons
Correlated Logistic Model With Elastic Net Regularization for Multilabel Image Classification
In this paper, we present correlated logistic (CorrLog) model for multilabel image classification.
On the Complexity of Learning Neural Networks
Moreover, this hard family of functions is realizable with a small (sublinear in dimension) number of activation units in the single hidden layer.
Deep Semi-Random Features for Nonlinear Function Approximation
For deep models, with no unrealistic assumptions, we prove universal approximation ability, a lower bound on approximation error, a partial optimization guarantee, and a generalization bound.
Diverse Neural Network Learns True Target Functions
In this paper, we answer these questions by analyzing one-hidden-layer neural networks with ReLU activation, and show that despite the non-convexity, neural networks with diverse units have no spurious local minima.
Scale Up Nonlinear Component Analysis with Doubly Stochastic Gradients
We propose a simple, computationally efficient, and memory friendly algorithm based on the "doubly stochastic gradients" to scale up a range of kernel nonlinear component analysis, such as kernel PCA, CCA and SVD.
Communication Efficient Distributed Kernel Principal Component Analysis
Can we perform kernel PCA on the entire dataset in a distributed and communication efficient fashion while maintaining provable and strong guarantees in solution quality?
Scalable Kernel Methods via Doubly Stochastic Gradients
The general perception is that kernel methods are not scalable, and neural nets are the methods of choice for nonlinear learning problems.
Nonparametric Estimation of Multi-View Latent Variable Models
We establish that the sample complexity for the proposed method is quadratic in the number of latent components and is a low order polynomial in the other relevant parameters.
