Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

10.4%20.8%31.2%41.7% · May 201919922001200920182026
48 results for Memory Augmented Neural Networks

Memory-augmented neural networks improve machine translation performance.

problem Improving machine translation accuracy and flexibility.
method Evaluation of Neural Turing Machines and Differentiable Neural Computers for machine translation tasks.
result Memory-augmented neural networks perform similarly to attentional encoders on Vietnamese to English tasks but have lower BLEU scores on Romanian to English tasks.

New memory in neural networks mimics computer architectures.

problem Learning algorithms and complex tasks with neural networks.
method Introducing a new memory to store weights for a neural controller, similar to stored-program memory in computers.
result Neural Stored-program Memory enhances neural networks' adaptability and learning capabilities.

MemNet optimizes neural architectures for memory efficiency.

problem Memory constraints in mobile devices limit the use of large neural networks.
method Augment-trim learning with memory consumption ranking score.
result MemNet finds architectures with 24.17% less memory usage compared to state-of-the-art methods.

This paper successfully implements Neural Turing Machines for sequence learning tasks.

problem Implementing stable and high-performing Neural Turing Machines.
method Detailed description and successful implementation of NTMs, focusing on memory contents initialization.
result Memory contents initialized to small constant values converge 2 times faster.

Recent empirical results on long-term dependency tasks have shown that neural networks augmented with an external memory can learn the long-term dependency tasks more easily and achieve better generalization than vanilla recurrent neural networks (RNN). We suggest that memory augmented neural networks can reduce the ef…

2017-01-30abs ↗pdf ↗

ARMIN improves memory efficiency and lightness in neural networks.

problem Complex memory addressing and inefficient memory information exploitation in previous MANNs.
method ARMIN uses hidden state for automatic memory addressing and a novel RNN cell for memory integration.
result ARMIN achieves lower computational overhead and similar performances compared to vanilla LSTM.

A new model learns preferences incrementally without personal data.

problem Incremental session-based recommendation without personal data.
method Memory Augmented Neural model (MAN) that combines a neural recommender with a nonparametric memory.
result MAN consistently outperforms existing methods in incremental session-based recommendation.

Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications. We propose a design of memory augmented neural networks (MANNs) called Labeled Memory Networks (LMNs) suited for tasks requiring online adaptation in class…

2017-07-05abs ↗pdf ↗

New method optimizes memory usage in neural networks, improving sequential learning.

problem Current memory models in neural networks waste memory and computation.
method Formulated an optimization problem to maximize information storage, introduced Cached Uniform Writing.
result Proved Cached Uniform Writing optimizes memory usage and outperforms other methods.

Memory augmented neural networks improve active learning for one-shot predictions.

problem Scarcity and cost of labeled training data in deep architectures.
method Memory augmented neural networks and Class Margin Sampling (CMS) for reinforcement learning.
result The proposed method outperforms existing baselines in label predictions and reduces label requests.

MAES architecture improves working memory task performance through multi-task and transfer learning.

problem Improving performance on complex working memory tasks.
method Memory-Augmented Encoder-Solver (MAES) architecture with dual recurrent neural network controllers and a shared memory module.
result MAES models achieve task-size generalization, handling inputs 50 times longer than training data.

Memory-Augmented Recurrent Networks improve dialogue coherence by expanding conversation history storage.

problem Fixed-size vectors limit dialogue coherence; attention mechanisms are computationally expensive.
method Introduce Neural Turing Machines (NTMs) to provide flexible and permanent storage for dialogue history.
result Improved perplexity performance compared to existing baselines.

Memory-augmented neural networks (MANNs) refer to a class of neural network models equipped with external memory (such as neural Turing machines and memory networks). These neural networks outperform conventional recurrent neural networks (RNNs) in terms of learning long-term dependency, allowing them to solve intrigui…

2017-11-10abs ↗pdf ↗

LEMN improves memory networks for learning from streaming data.

problem Efficiently processing large data streams in memory-augmented neural networks.
method LEMN uses a RNN-based retention agent to learn and replace less important memory entries based on their importance and historical context.
result LEMN achieves significant improvements over existing methods in learning from streaming data.

Paper proposes a new neural network for predicting machinery RUL.

problem Accurately estimating the remaining useful life of industrial machinery.
method Temporal Convolutional Memory Networks incorporating long and short term dependencies.
result Demonstrates superior performance compared to state-of-the-art algorithms.

Deep neural networks estimate long memory parameters efficiently.

problem Estimating long memory parameters in stochastic processes.
method Scale-invariant 1D Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) models trained with synthetic data.
result Neural models outperform conventional methods in precision, speed, consistency, and robustness.

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read}, compose and write operations. NSE c…

2016-07-14abs ↗pdf ↗

Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on "meta-learning…

2017-10-19abs ↗pdf ↗

Sparse Meta Networks adapt deep neural networks incrementally for fast learning.

problem Training deep neural networks is slow and impractical for complex, changing environments.
method Sparse Meta Networks use a memory layer to learn online sequential adaptation, accumulating fast-weights incrementally.
result Sparse Meta Networks achieve strong performance in various sequential adaptation scenarios.

Paper shows how LSTM can remember long sequences by attending to persisted information.

problem LSTMs struggle with long sequences due to fading information and bias towards recent data.
method The paper introduces a mechanism that allows LSTMs to attend to information in memory based on how long it was persisted by the gating mechanism.
result The method improves LSTM's ability to process long sequences by retrieving information proportionally to its persistence in memory.

A new method reduces memory requirements for Graph Transformers by sparsely training a network.

problem Quadratic memory complexity in Graph Transformers limits their scalability to large graphs.
method Spexphormer: trains a narrow network on augmented graph, then uses only active connections in a wider network.
result Spexphormer achieves good performance with drastically reduced memory requirements.

MEMGAN uses memory to improve anomaly detection by isolating abnormal data.

problem Weak guarantees for detecting anomalous data in classical algorithms.
method Memory-augmented Generative Adversarial Networks (MEMGAN) with a memory module.
result MEMGAN provides strong guarantees for anomaly detection with improved reconstruction.

DAM with MRL improves relational reasoning in MANNs.

problem Limited performance of associative memory networks on complex relational reasoning tasks.
method Distributed Associative Memory architecture with Memory Refreshing Loss.
result Enhanced relation reasoning performance of MANNs on long temporal sequence data.

A method to reduce memory usage in deep learning models by adding inducing weights.

problem Memory inefficiency in Bayesian neural networks and deep ensembles.
method Augmenting the weight matrix with inducing weights and using Matheron's conditional Gaussian sampling rule.
result Reduces parameter size to 24.3% of a single neural network while maintaining competitive performance.

The explosion in workload complexity and the recent slow-down in Moore's law scaling call for new approaches towards efficient computing. Researchers are now beginning to use recent advances in machine learning in software optimizations, augmenting or replacing traditional heuristics and data structures. However, the s…

2018-03-06abs ↗pdf ↗

This paper improves GNNs' generalization by adding a Low-Rank Global Attention module.

problem Improving the generalization power of Graph Neural Networks (GNNs).
method Incorporating a Low-Rank Global Attention (LRGA) module into GNNs.
result Augmenting GNNs with LRGA aligns them with a powerful graph isomorphism test, 2-Folklore Weisfeiler-Lehman (2-FWL).

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 …

2017-09-08abs ↗pdf ↗

CLA improves investment accuracy by leveraging past knowledge.

problem Improving investment decisions through past knowledge integration.
method CLA uses an explicit memory structure and FFNN base model, incorporating change points and contextual similarity.
result CLA significantly outperforms FFNN base models in expected return forecasting.

GAMENet uses graph memory networks to recommend safe medication combinations.

problem Lack of personalized and safe medication combination recommendations considering patient history and drug interactions.
method Integrates drug-drug interactions knowledge graph into a memory module using graph convolutional networks and models longitudinal patient records.
result GAMENet outperformed state-of-the-art methods in effectiveness and safety, reducing DDI rate by 3.60%.

Deep RL agents suffer from transient non-stationarity, which ITER mitigates.

problem Transient non-stationarity in deep RL agents affects generalization.
method Iterated Relearning (ITER) transfers knowledge between networks to reduce non-stationarity.
result ITER improves deep RL agents' performance on generalization benchmarks.

Paper tackles many-class few-shot learning with class hierarchy, improving accuracy.

problem Many-class few-shot learning problem in practical applications.
method Leverages class hierarchy to train a coarse-to-fine classifier using memory-augmented hierarchical-classification network (MahiNet).
result MahiNet outperforms state-of-the-art models on MCFS problems in both supervised and meta-learning settings.

Survey of data augmentation techniques for time series classification with neural networks.

problem Small datasets in time series recognition.
method Four families of data augmentation: transformation-based, pattern mixing, generative models, and decomposition methods.
result Empirical evaluation of 12 data augmentation methods on 128 datasets.

HomoODE connects DEQs and Neural ODEs via homotopy continuation, improving accuracy and memory efficiency.

problem Connecting DEQs and Neural ODEs for better model performance and efficiency.
method Established a connection between DEQs and Neural ODEs using homotopy continuation, proposing HomoODE.
result HomoODE outperforms existing implicit models in accuracy and memory consumption.