GitHub

Bankai: Ultra-Sparse Adaptation of 1-Bit LLMs via XOR Patches

Without patch: d/dx [x^7 + x] = 0 With patch: d/dx [x^7 + x] = 7x^6 + 1 Without patch: Is 113 prime? No, 113 is not prime With patch: Is 113 prime? Yes, 113 is a prime number True 1-bit LLMs have no ...
GitHub

Online Sparse Dictionary Learning Algorithm

This is the Matlab Package for the Online Sparse Dictionary Learning (OSDL) algorithm, presented in: J. Sulam, B. Ophir, M. Zibulevsky and M. Elad, "Trainlets: Dictionary Learning in High Dimensions," ...
IEEE

Online Sparse Gaussian Process Regression and Its Applications

Abstract: We present a new Gaussian process (GP) inference algorithm, called online sparse matrix Gaussian processes (OSMGP), and demonstrate its merits by applying it to the problems of head pose ...
IEEE

A Balanced Sparse Matrix Convolution Accelerator for Efficient CNN Training

Abstract: Sparse Convolutional Neural Network (CNN) training is well known to be time-consuming due to significant off-chip memory traffic. To effectively deploy sparse training, existing accelerators ...
Frontiers

Human behavior recognition based on sparse transformer with channel attention mechanism

Human activity recognition (HAR) has recently become a popular research field in the wearable sensor technology scene. By analyzing the human behavior data, some disease risks or potential health ...
CU Boulder News & Events

Data Analytics Best Practices: Best Machine Learning Model for Sparse Data

Sparse data can impact the effectiveness of machine learning models. As students and experts alike experiment with diverse datasets, sparse data poses a challenge. The Leeds Master’s in Business ...
Scientific Research Publishing

A Double-Weighted Deterministic Extreme Learning Machine Based on Sparse Denoising Autoencoder and Its Applications ()

1 College of Computer Science and Engineering, Jishou University, Jishou, China. 2 College of Computer and Artificial Intelligence, Huaihua University, Huaihua, China. Extreme learning machine (ELM) ...