4 papers
DIP-GS: Deep Image Prior For Gaussian Splatting Sparse View Recovery
Rajaei Khatib, Raja Giryes
3D Gaussian Splatting (3DGS) is a leading 3D scene reconstruction method, obtaining high-quality reconstruction with real-time rendering runtime performance. The main idea behind 3…
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…
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…