Related papers: Theano: new features and speed improvements
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers -…
We present a new tool for training neural network language models (NNLMs), scoring sentences, and generating text. The tool has been written using Python library Theano, which allows researcher to easily extend it and tune any aspect of the…
Deep learning methods have resulted in significant performance improvements in several application domains and as such several software frameworks have been developed to facilitate their implementation. This paper presents a comparative…
We present Synkhronos, an extension to Theano for multi-GPU computations leveraging data parallelism. Our framework provides automated execution and synchronization across devices, allowing users to continue to write serial programs without…
Deep neural networks (DNNs) have been proving the effectiveness in various computing fields. To provide more efficient computing platforms for DNN applications, it is essential to have evaluation environments that include assorted benchmark…
The translation of linear algebra computations into efficient sequences of library calls is a non-trivial task that requires expertise in both linear algebra and high-performance computing. Almost all high-level languages and libraries for…
A major challenge in the deployment of scientific software solutions is the adaptation of research prototypes to production-grade code. While high-level languages like MATLAB are useful for rapid prototyping, they lack the resource…
We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel. Blocks is based on Theano, a linear algebra compiler with CUDA-support. It facilitates the training of complex neural network models by…
Tensor Networks have emerged as a prominent alternative to neural networks for addressing Machine Learning challenges in foundational sciences, paving the way for their applications to real-life problems. This paper introduces tn4ml, a…
In this paper, we present Ginkgo, a modern C++ math library for scientific high performance computing. While classical linear algebra libraries act on matrix and vector objects, Ginkgo's design principle abstracts all functionality as…
This paper introduces SpeedLLM, a neural network accelerator designed on the Xilinx Alevo U280 platform and optimized for the Tinyllama framework to enhance edge computing performance. Key innovations include data stream parallelism, a…
Supervised machine learning has become the cornerstone of today's data-driven society, increasing the need for labeled data. However, the process of acquiring labels is often expensive and tedious. One possible remedy is to use active…
In this paper, we present nmtpy, a flexible Python toolkit based on Theano for training Neural Machine Translation and other neural sequence-to-sequence architectures. nmtpy decouples the specification of a network from the training and…
We present Rhino, a system for accelerating tensor programs with automatic parallelization on AI platform for real production environment. It transforms a tensor program written for a single device into an equivalent distributed program…
Conan is a C++ library created for the accurate and efficient modelling, inference and analysis of complex networks. It implements the generation and modification of graphs according to several published models, as well as the unexpensive…
Limbo is an open-source C++11 library for Bayesian optimization which is designed to be both highly flexible and very fast. It can be used to optimize functions for which the gradient is unknown, evaluations are expensive, and runtime cost…
Graph Neural Networks (GNNs) use a fully-connected layer to extract features from the nodes of a graph and aggregate these features using message passing between nodes, combining two distinct computational patterns: dense, regular…
We introduce a learning-based framework to optimize tensor programs for deep learning workloads. Efficient implementations of tensor operators, such as matrix multiplication and high dimensional convolution, are key enablers of effective…
PENLAB is an open source software package for nonlinear optimization, linear and nonlinear semidefinite optimization and any combination of these. It is written entirely in MATLAB. PENLAB is a young brother of our code PENNON \cite{pennon}…
ALAMO is a computational methodology for leaning algebraic functions from data. Given a data set, the approach begins by building a low-complexity, linear model composed of explicit non-linear transformations of the independent variables.…