Related papers: Adaptive Memory Networks

We introduce an Artificial Neural Network (ANN) quantization methodology for platforms without wide accumulation registers. This enables fixed-point model deployment on embedded compute platforms that are not specifically designed for large…

In multimodal machine learning tasks, it is due to the complexity of the assignments that the network structure, in most cases, is assembled in a sophisticated way. The holistic architecture can be separated into several logical parts…

In this article we propose a new deep learning approach to approximate operators related to parametric partial differential equations (PDEs). In particular, we introduce a new strategy to design specific artificial neural network (ANN)…

Emergency communications networks require in-network intelligence for timely traffic handling under dynamic demands and runtime constraints. In these environments, packets may need different inference behaviors, and conventional model…

Transformer networks, driven by self-attention, are central to Large Language Models. In generative Transformers, self-attention uses cache memory to store token projections, avoiding recomputation at each time step. However, GPU-stored…

Sequential memory, the ability to form and accurately recall a sequence of events or stimuli in the correct order, is a fundamental prerequisite for biological and artificial intelligence as it underpins numerous cognitive functions (e.g.,…

The increasing usage of Artificial Intelligence (AI) models, especially Deep Neural Networks (DNNs), is increasing the power consumption during training and inference, posing environmental concerns and driving the need for more…

Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal,…

We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to…

Generative adversarial networks (GANs) are successfully used for image synthesis but are known to face instability during training. In contrast, probabilistic diffusion models (DMs) are stable and generate high-quality images, at the cost…

With the increasing use of nonlinear devices in both generation and consumption of power, it is essential that we develop accurate and quick control for active filters to suppress harmonics. Time delays between input and output are…

While Annealing Machines (AM) have shown increasing capabilities in solving complex combinatorial problems, positioning themselves as a more immediate alternative to the expected advances of future fully quantum solutions, there are still…

What do artificial neural networks (ANNs) learn? The machine learning (ML) community shares the narrative that ANNs must develop abstract human concepts to perform complex tasks. Some go even further and believe that these concepts are…

This work considers the trade-off between accuracy and test-time computational cost of deep neural networks (DNNs) via \emph{anytime} predictions from auxiliary predictions. Specifically, we optimize auxiliary losses jointly in an…

Recent advances in machine-learning interatomic potentials have enabled the efficient modeling of complex atomistic systems with an accuracy that is comparable to that of conventional quantum mechanics based methods. At the same time, the…

Capturing users' precise preferences is of great importance in various recommender systems (eg., e-commerce platforms), which is the basis of how to present personalized interesting product lists to individual users. In spite of significant…

We develop a data-driven model, introducing recent advances in machine learning to reservoir simulation. We use a conventional reservoir modeling tool to generate training set and a special ensemble of artificial neural networks (ANNs) to…

Deep neural networks have significantly improved performance on a range of tasks with the increasing demand for computational resources, leaving deployment on low-resource devices (with limited memory and battery power) infeasible. Binary…

We study a sequential mechanism design problem in which a principal seeks to elicit truthful reports from multiple rational agents while starting with no prior knowledge of agents' beliefs. We introduce Distributionally Robust Adaptive…

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes…