4 papers · 1 filter
Revisiting Glorot Initialization for Long-Range Linear Recurrences
Noga Bar, Mariia Seleznova, Yotam Alexander +2
Proper initialization is critical for Recurrent Neural Networks (RNNs), particularly in long-range reasoning tasks, where repeated application of the same weight matrix can cause v…
ZOQO: Zero-Order Quantized Optimization
Noga Bar, Raja Giryes
The increasing computational and memory demands in deep learning present significant challenges, especially in resource-constrained environments. We introduce a zero-order quantize…
Diverse Subset Selection via Norm-Based Sampling and Orthogonality
Noga Bar, Raja Giryes
Large annotated datasets are crucial for the success of deep neural networks, but labeling data can be prohibitively expensive in domains such as medical imaging. This work tackles…
Introduction to deep learning
Lihi Shiloh-Perl, Raja Giryes
Deep Learning (DL) has made a major impact on data science in the last decade. This chapter introduces the basic concepts of this field. It includes both the basic structures used…