arXiv research

STanHop predicts multivariate time series with memory-enhanced capabilities.

Enhanced Hopfield model boosts memory retrieval capacity.

In this paper, we present Gamma-LSTM, an enhanced long short term memory (LSTM) unit, to enable learning of hierarchical representations through multiple stages of temporal abstractions. Gamma memory, a hierarchical memory unit, forms the central memory of Gamma-LSTM with gates to regulate the information flow into var…

FinMem enhances LLM trading agents with layered memory and character design.

Enhanced financial trading system using multi-agent LLMs with layered memory.

Enhances sequence memory capacity in neural networks.

DAM with MRL improves relational reasoning in MANNs.

This paper optimizes SMPC for neural network inference, reducing memory and time.

Enhances option pricing with fractional order Black-Scholes-Merton model.

New cooperative dynamics enhances retrieval performance in neural networks.

Improved fraud detection in finance with quantum-enhanced federated learning.

Stable Hadamard Memory improves reinforcement learning by efficiently managing memory.

In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks. However, previous MANNs suffer from complex memory addressing mechanism, making them relatively hard to train and causing computational overheads. Moreove…

Fully convolutional neural networks (FCN) have been shown to achieve state-of-the-art performance on the task of classifying time series sequences. We propose the augmentation of fully convolutional networks with long short term memory recurrent neural network (LSTM RNN) sub-modules for time series classification. Our …

Point-of-Interest (POI) recommender systems play a vital role in people's lives by recommending unexplored POIs to users and have drawn extensive attention from both academia and industry. Despite their value, however, they still suffer from the challenges of capturing complicated user preferences and fine-grained user…

LSTMs and GRUs are the most common recurrent neural network architectures used to solve temporal sequence problems. The two architectures have differing data flows dealing with a common component called the cell state (also referred to as the memory). We attempt to enhance the memory by presenting a modification that w…

MIP framework improves urban flow prediction by adapting to distribution shifts.

Enhanced Momentum Transformer outperforms traditional trading strategies.

A novel memory mechanism for reinforcement learning agents that stores past events in human-readable language.

The study analyzes prediction errors in systems with memory kernels, providing bounds and stability results.

New neural networks model complex phenomena with fewer parameters.

Efficiently discovers Bayesian network structure with reduced memory usage.

Paper proposes efficient optimizers for large language models with fast convergence and low memory usage.

Partially observable environments present an important open challenge in the domain of sequential control learning with delayed rewards. Despite numerous attempts during the two last decades, the majority of reinforcement learning algorithms and associated approximate models, applied to this context, still assume Marko…

V-HMN integrates memory mechanisms for improved image recognition.

AlphaGrad optimizes memory usage in RL algorithms by normalizing gradients.

Gravitational wave memory increases faster than Brownian motion in early universe and astrophysical sources.

A new memory-based fusion layer improves multi-modal deep learning performance.

Quantum memory limits set by relativity theory.

Time series forecasting is an important problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. In this paper, we propose to tackle such forecasting problem with Transformer [1]. Although impressed by its performance in our preliminary study, …

HTE improves PINNs for high-dimensional, high-order PDEs by reducing computational cost and memory usage.

RSmote improves PINNs accuracy with less memory usage.

Study uses LSTM models to detect Wyckoff patterns in currency trading.

In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate a compact representation of the current dialog status from a sequence of noisy observations produced by the speech recognition and the natural language understanding modules. This paper introduces a novel method of dialog state t…

TinyLSTMs reduces speech enhancement model size and latency for hearing aids.

Study enhances neural network predictions for wave height using topological features.

The holy grail in deep neural network research is porting the memory- and computation-intensive network models on embedded platforms with a minimal compromise in model accuracy. To this end, we propose a novel approach, termed as Variational Student, where we reap the benefits of compressibility of the knowledge distil…

Improved speech enhancement with MNTFA using time-frequency attention.

Classification of seizure type is a key step in the clinical process for evaluating an individual who presents with seizures. It determines the course of clinical diagnosis and treatment, and its impact stretches beyond the clinical domain to epilepsy research and the development of novel therapies. Automated identific…

Enhanced multivariate GARCH model using LSTM for better volatility forecasting.

One of the major challenges in training deep architectures for predictive tasks is the scarcity and cost of labeled training data. Active Learning (AL) is one way of addressing this challenge. In stream-based AL, observations are continuously made available to the learner that have to decide whether to request a label …

This paper investigates the role of sparsity in Reservoir Computing networks.

Widely popular transformer-based NLP models such as BERT and Turing-NLG have enormous capacity trending to billions of parameters. Current execution methods demand brute-force resources such as HBM devices and high speed interconnectivity for data parallelism. In this paper, we introduce a new relay-style execution tec…

Enhanced portfolio selection using sentiment data and LSTM.

Study uses IMFs and neural networks to predict economic time series, enhancing interpretability.

LORENZA improves LLM fine-tuning efficiency and generalization.

With the arrival of the big data era, more and more data are becoming readily available in various real-world applications and those data are usually highly heterogeneous. Taking computational medicine as an example, we have both Electronic Health Records (EHR) and medical images for each patient. For complicated disea…

Enhanced Neural ODEs outperform traditional models in image classification and video prediction.