paper-with-me

Papers

No Saved Kaleidosope: an 100% Jitted Neural Network Coding Language with Pythonic Syntax

2024-09-17 · Augusto Seben da Rosa, Marlon Daniel Angeli, Jorge Aikes Junior, Alef Iury Ferreira, Lucas Rafael Gris, Anderson da Silva Soares, Arnaldo Candido Junior, Frederico Santos de Oliveira, Gabriel Trevisan Damke, Rafael Teixeira Sousa

We developed a jitted compiler for training Artificial Neural Networks using C++, LLVM and Cuda. It features object-oriented characteristics, strong typing, parallel workers for data pre-processing, pythonic syntax for expressions, PyTorch like model declaration and Automatic Differentiation. We implement the mechanisms of cache and pooling in order to manage VRAM, cuBLAS for high performance matrix multiplication and cuDNN for convolutional layers. Our experiments with Residual Convolutional Neural Networks on ImageNet, we reach similar speed but degraded performance. Also, the GRU network experiments show similar accuracy, but our compiler have degraded speed in that task. However, our compiler demonstrates promising results at the CIFAR-10 benchmark, in which we reach the same performance and about the same speed as PyTorch. We make the code publicly available at: https://github.com/NoSavedDATA/NoSavedKaleidoscope

📄 PDF Abstract BibTeX arXiv:2409.11600

Code (1)

nosaveddata/nosavedkaleidoscope 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Phyelds: A Pythonic Framework for Aggregate Computing

2026-03-31 · Gianluca Aguzzi, Davide Domini, Nicolas Farabegoli, Mirko Viroli arxiv

Aggregate programming is a field-based coordination paradigm with over a decade of exploration and successful applications across domains including sensor networks, robotics, and IoT, with implementations in various prog…

Multi-agent Reinforcement LearningFederated Learning

SAVeD: Semantic Aware Version Discovery

2025-11-21 · Artem Frenk, Roee Shraga arxiv

Our work introduces SAVeD (Semantically Aware Version Detection), a contrastive learning-based framework for identifying versions of structured datasets without relying on metadata, labels, or integration-based assumptio…

Contrastive LearningSemantic Similarity

Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search

2024-05-26 · Max Liu, Chan-Hung Yu, Wei-Hsu Lee, Cheng-Wei Hung 외

Programmatic reinforcement learning (PRL) has been explored for representing policies through programs as a means to achieve interpretability and generalization. Despite promising outcomes, current state-of-the-art PRL m…

Common Sense ReasoningLanguage ModelingLanguage ModellingLarge Language Model

A Pythonic Functional Approach for Semantic Data Harmonisation in the ILIAD Project

2026-02-27 · Erik Johan Nystad, Francisco Martín-Recuerda arxiv

Semantic data harmonisation is a central requirement in the ILIAD project, where heterogeneous environmental data must be harmonised according to the Ocean Information Model (OIM), a modular family of ontologies for enab…

Power-Efficient Video Streaming on Mobile Devices Using Optimal Spatial Scaling

2023-07-17 · Christian Herglotz, André Kaup, Stéphane Coulombe, Ahmad Vakili

This paper derives optimal spatial scaling and rate control parameters for power-efficient wireless video streaming on portable devices. A video streaming application is studied, which receives a high-resolution and high…