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.
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.
ORIGAMI accelerates ML algorithms by splitting compute tasks between in-memory and off-chip accelerators.
problem Memory bandwidth bottleneck in ML processing.
method Heterogeneous in-memory accelerators and off-chip compute platform, pattern-matching for compute patterns, computation-splitting compiler.
result ORIGAMI outperforms state-of-the-art accelerators in performance and energy-efficiency.
Low-rank training improves neural network training on edge devices with non-volatile memory.
problem Training neural networks on edge devices with non-volatile memory, especially in terms of write density and auxiliary memory.
method Low-rank training scheme to address write density and auxiliary memory limitations.
result The low-rank training technique outperforms standard SGD in accuracy and weight writes.
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…
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.
New memory effect discovered in gravitational wave behavior.
problem Understanding gravitational wave behavior in spacetimes with angular momentum.
method Mathematical analysis of Minkowski spacetime and Kerr black holes.
result Angular momentum memory effect observed at future null infinity.
Generative memory helps AI learn new tasks without forgetting old ones.
problem Catastrophic forgetting in lifelong reinforcement learning.
method Generative memory model for task-agnostic latent space.
result Generative memory can improve lifelong reinforcement learning performance.
An associative memory is a framework of content-addressable memory that stores a collection of message vectors (or a dataset) over a neural network while enabling a neurally feasible mechanism to recover any message in the dataset from its noisy version. Designing an associative memory requires addressing two main task…
The properties of statistical tests for hypotheses concerning the parameters of the multifractal model of asset returns (MMAR) are investigated, using Monte Carlo techniques. We show that, in the presence of multifractality, conventional tests of long memory tend to over-reject the null hypothesis of no long memory. Ou…
This paper optimizes SMPC for neural network inference, reducing memory and time.
problem Memory and time constraints in secure neural network inference.
method Implemented ABY2.0 protocol, optimized memory usage, and used a helper node.
result MNIST inference reduced from 8.03 GB RAM and 200s to 0.2 GB RAM and 32s.
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which …
The Long-Short-Term-Memory Recurrent Neural Networks (LSTM RNNs) are a popular class of machine learning models for analyzing sequential data. Their training on modern GPUs, however, is limited by the GPU memory capacity. Our profiling results of the LSTM RNN-based Neural Machine Translation (NMT) model reveal that fea…
New methods improve neural network extrapolation to long sequences.
problem Neural networks struggle with extrapolation to very long or adversarial sequences.
method Activation binning and localized differentiable memory architecture.
result No extrapolation errors detected within memory constraints.
XLA compiler extension improves memory efficiency for machine learning.
problem Memory constraints limit the scalability of memory-intensive machine learning algorithms.
method Developed an XLA compiler extension that adjusts algorithm data-flow representation to fit memory limits.
result k-nearest neighbour and sparse Gaussian process regression can be run at larger scales.
Enhanced image recognition models learn from human-like memory and shape biases.
problem Improving robustness of image recognition models against various perturbations.
method Integrating human-like episodic memory and shape bias features into image recognition models.
result Combining human-like features improves robustness against both adversarial and natural perturbations.
SINGD improves KFAC for memory-efficiency and stability in low-precision training.
problem Memory inefficiency and numerical instability of KFAC in low-precision training.
method Formulated inverse-free KFAC update and imposed structures in Kronecker factors.
result SINGD is memory-efficient and numerically robust, often outperforming AdamW in half precision.
Experience replay is a key technique behind many recent advances in deep reinforcement learning. Allowing the agent to learn from earlier memories can speed up learning and break undesirable temporal correlations. Despite its wide-spread application, very little is understood about the properties of experience replay. …
LTM tackles long sequence language modeling by avoiding vanishing and exploding gradients.
problem Language models struggle with long sequences due to gradient issues.
method Introduces Long Term Memory network (LTM) that scales memory and weights input, avoiding overfitting.
result LTM achieves state-of-the-art perplexity results with fewer cells than previous models.
One of the core tasks in multi-view learning is to capture relations among views. For sequential data, the relations not only span across views, but also extend throughout the view length to form long-term intra-view and inter-view interactions. In this paper, we present a new memory augmented neural network model that…
PARMESAN learns from memory without parameters for fast, efficient continual learning.
problem Inflexibility in deep learning methods for continual learning.
method Transductive reasoning and memory search for parameter-free learning.
result 3-4 orders of magnitude faster than baselines, comparable performance.
EAST compresses deep ConvNets for tiny memory nodes.
problem Memory constraints in tiny devices for deep ConvNets.
method Encoding-Aware Sparse Training (EAST) with adaptive group pruning and LZ4 weight encoding.
result EAST achieves deep memory compression with lower sparsity and higher accuracy.
SPARC improves continual learning with minimal memory and computational overhead.
problem Efficient continual learning for deep neural networks.
method Combines task-specific working memories and task-agnostic semantic memory.
result Significantly reduces parameter usage (6% of full-model surrogates) while maintaining performance.
SDA method reduces memory and time for assimilating noisy geophysical data.
problem Challenges in identifying state trajectories of high-dimensional geophysical systems.
method Score-based data assimilation with modified score network architecture.
result Promising results for a two-layer quasi-geostrophic model.
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…
A new model MTNet uses memory networks for better time series forecasting.
problem Challenges in modeling complex patterns and dependencies in multivariate time series data.
method Memory Time-series network (MTNet) with a large memory component, three encoders, and an autoregressive component.
result MTNet effectively captures long-term patterns and incorporates information from other variables.
Efficiently scales continuous kernels with sparse Fourier domain learning.
problem High computational and memory demands, spectral bias in continuous kernels.
method Sparse learning in the Fourier domain.
result Efficient scaling of continuous kernels, reduced computational and memory requirements, mitigated spectral bias.
Serenity optimizes neural network execution for edge devices by scheduling with optimal memory footprint.
problem Order of nodes in irregular neural networks affects memory footprint, complicating execution under resource constraints.
method Memory-aware compiler using dynamic programming and graph rewriting to find optimal schedules.
result Achieves optimal peak memory and further improves it with graph rewriting, reducing memory usage by 1.68x-1.86x compared to TensorFlow Lite.
Neural ARFIMA model improves exchange rate forecasting for BRIC economies.
problem Forecasting exchange rates for emerging markets with long-term memory and nonlinear dynamics.
method Integrates ARFIMA for long-memory with neural networks for nonlinear approximation.
result NARFIMA model outperforms benchmarks in BRIC exchange rate forecasting.
Bandana stores deep learning models using NVM with DRAM caching.
problem Reducing memory footprint of deep learning models stored on DRAM.
method Uses NVM as primary storage, DRAM as cache, hypergraph partitioning, and cache simulation.
result Significantly reduces the cost of ownership for storing deep learning models.
NPAS trains neural networks with a fixed parameter budget, improving performance and compactness.
problem Training neural networks requires memory, and existing methods struggle with arbitrary parameter budgets.
method NPAS learns to share parameters automatically, covering low and high budgets.
result NPAS and SSNs improve network performance and compactness across various tasks.
A new memory model enhances deep learning's visual understanding.
problem Lack of short-term memory in deep learning models.
method Introduces a biologically inspired visual working memory architecture.
result Model achieves competitive classification performance and reconstructs images.
New algorithms for streaming bandits with limited memory.
problem Optimizing decisions in a stream of uncertain outcomes with limited memory.
method Developed algorithms for minimizing regret and identifying the best arm under bounded memory constraints.
result Upper and lower bounds on sample complexity for best-arm identification algorithms.
We address the problem of long-range memory in the financial markets. There are two conceptually different ways to reproduce power-law decay of auto-correlation function: using fractional Brownian motion as well as non-linear stochastic differential equations. In this contribution we address this problem by analyzing e…
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…
PySAD offers a unified Python framework for efficient streaming anomaly detection.
problem Efficient anomaly detection in streaming data with strict constraints.
method Unified architecture with 17+ streaming algorithms, specialized components, and support for multiple learning paradigms.
result PySAD enables real-time processing with bounded memory and is compatible with other Python frameworks.
The study examines how investor protection and past information affect stock returns and interest rates.
problem Empirical regularities related to investor protection and past information in asset pricing models.
method Developed a dynamic asset pricing model with a controlling shareholder and good/bad memory in budget dynamics.
result Good/bad memory of investors on historical market information affects stock returns and interest rates, strengthening investor protection in high ownership concentration.
N-BEATS(P) efficiently forecasts millions of time series with reduced memory and time.
problem Efficiently forecasting millions of time series with high accuracy.
method Global parallel variant of N-BEATS model designed for multi-step time series forecasting.
result Significant reduction in training time and memory usage with comparable accuracy.
SketchOGD improves memory efficiency for continual learning.
problem Catastrophic forgetting in continual learning.
method Matrix sketching to compress model gradients.
result SketchOGD outperforms existing memory-efficient OGD variants.
ENRNN uses eigenvalue normalization for short-term memory in RNNs.
problem Vanishing/exploding gradient problem and long-term dependency modeling.
method Eigenvalue normalization of recurrent matrix to simulate short-term memory.
result ENRNN outperforms existing RNN variants in experiments.
AlphaGrad optimizes memory usage in RL algorithms by normalizing gradients.
problem Memory overhead and hyperparameter complexity in adaptive optimizers.
method Tensor-wise L2 normalization followed by a smooth hyperbolic tangent transformation controlled by a single parameter.
result AlphaGrad provides enhanced training stability and competitive performance in various RL algorithms.
This paper tackles federated incremental learning with dynamic memory allocation for improved model performance in non-IID data.
problem Catastrophic forgetting in federated healthcare systems with non-IID data.
method Dynamic memory allocation strategy based on data replay mechanism.
result Significant performance improvements in medical image datasets compared to baseline models.
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.
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…
A Kalman Optimiser improves continual learning in deep neural networks.
problem Learning new tasks sequentially without forgetting previously learned knowledge.
method Divides the neural network into long-term and short-term memory units.
result The method enables continual learning and adaptation without forgetting.
Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the memory cells mean an LSTM layer has four times as many parameters as an RNN with the…
Prototype-based generative replay framework for online continual regression.
problem Addressing the challenge of non-stationary data streams in regression tasks.
method Adaptive output-space discretization model for prototype-based generative replay.
result Reduces forgetting and provides more stable performance.
New algorithms achieve optimal regret in sliding window model with limited memory.
problem Experts problem in the sliding window model with limited information.
method 2 queries, polylog(nT) memory, exponential improvement on memory.
result Achieve optimal regret of sqrt(nW)polylog(nT) with 2 queries and polylog(nT) memory.