Related papers: TensorNEAT: A GPU-accelerated Library for NeuroEvo…

Evolutionary algorithms (EAs) provide unique advantages for optimizing neural networks in complex search spaces. This paper introduces a new web platform, NeuroEvo (neuroevo.io), that allows users to interactively design and train neural…

Graph Neural Networks (GNNs) are becoming a promising technique in various domains due to their excellent capabilities in modeling non-Euclidean data. Although a spectrum of accelerators has been proposed to accelerate the inference of…

Scientific problems require resolving multi-scale phenomena across different resolutions and learning solution operators in infinite-dimensional function spaces. Neural operators provide a powerful framework for this, using…

Recent developments within memory-augmented neural networks have solved sequential problems requiring long-term memory, which are intractable for traditional neural networks. However, current approaches still struggle to scale to large…

We introduce an output layer for neural networks that ensures satisfaction of convex constraints. Our approach, $\Pi$net, leverages operator splitting for rapid and reliable projections in the forward pass, and the implicit function theorem…

This paper presents an adaptive convolutional neural network (CNN) architecture that can automate diverse topology optimization (TO) problems having different underlying physics. The architecture uses the encoder-decoder networks with dense…

Stochastic gradient descent (SGD) is a premium optimization method for training neural networks, especially for learning objectively defined labels such as image objects and events. When a neural network is instead faced with subjectively…

Combinatorial optimization is essential across numerous disciplines. Traditional metaheuristics excel at exploring complex solution spaces efficiently, yet they often struggle with scalability. Deep learning has become a viable alternative…

Graph Neural Networks (GNNs) are vital for learning from graph-structured data, enabling applications in network analysis, recommendation systems, and speech analytics. Deploying them on edge devices like client PCs and laptops enhances…

AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention. Our framework is inspired by the AdaNet algorithm (Cortes et al., 2017) which learns…

ATM-Net is a novel neural network architecture tailored for energy-harvested IoT devices, integrating adaptive termination points with multi-precision computing. It dynamically adjusts computational precision (32/8/4-bit) and network depth…

Recent advancements in artificial intelligence, particularly deep neural networks, have pushed the boundaries of what is achievable in complex tasks. Traditional methods for training neural networks in classification problems often rely on…

This paper presents the Tensor Product Network (TPNet), a novel neural architecture for efficient and accurate function approximation and PDE solving. The core of the proposal involves constructing the solution explicitly as a linear…

BERT-enhanced neural machine translation (NMT) aims at leveraging BERT-encoded representations for translation tasks. A recently proposed approach uses attention mechanisms to fuse Transformer's encoder and decoder layers with BERT's…

Neural networks have proved to be very robust at processing unstructured data like images, text, videos, and audio. However, it has been observed that their performance is not up to the mark in tabular data; hence tree-based models are…

Recurrent neural networks (RNNs) are powerful tools for sequential modeling, but typically require significant overparameterization and regularization to achieve optimal performance. This leads to difficulties in the deployment of large…

Transformer-based autoregressive models offer an efficient alternative to diffusion- and flow-matching-based approaches for generating 3D molecules. One challenge remains: standard transformer architectures require a sequential ordering of…

As the role of artificial intelligence becomes increasingly pivotal in modern society, the efficient training and deployment of deep neural networks have emerged as critical areas of focus. Recent advancements in attention-based large…

Graph neural networks (GNNs) are powerful models that have been successful in various graph representation learning tasks. Whereas gradient boosted decision trees (GBDT) often outperform other machine learning methods when faced with…

High-performance deep learning depends on efficient tensor programs. In recent years, automatic tensor program optimization, also known as tensor compilation, has emerged as the primary approach to generating efficient tensor programs.…