Search Articles
Deep Learning for Educational Video Analysis: Benchmarking ASR Systems and Pipeline Optimization
We present a comparative analysis of eight managed commercial speech recognition providers (provider-side preprocessing, segmentation, and serving) for educational video transcription and enrichment,...
OLORA+: A HYBRID APPROACH TO PARAMETER- EFFICIENT FINE-TUNING OF LARGE LANGUAGE MODELS
Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs) under resource constraints, yet existing methods often treat initialization and optimization as separate c...
Separate Adjustment of Linear and Nonlinear Parameters in Neural Network Training
The paper examines the limitations of the backpropagation error (BPE) method in neural network training, particularly its tendency to converge to suboptimal local minima. Traditional backpropagation-b...