We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning. We conceptualize this memory as a rapidly adaptable function that we parameterize as a deep neural network. Reading from the neural memory function amounts to pushing an input (the key vector) throug…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “neural memories”
Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern…
In this paper, a taxonomy for memory networks is proposed based on their memory organization. The taxonomy includes all the popular memory networks: vanilla recurrent neural network (RNN), long short term memory (LSTM ), neural stack and neural Turing machine and their variants. The taxonomy puts all these networks und…
Reservoir Memory Machines solve benchmark tasks faster than Neural Turing Machines.
problem Training Neural Turing Machines is hard and limits their applicability.
method Proposes Reservoir Memory Machines, combining neural network flexibility with Turing machine capabilities, but with faster training via alignment and linear regression.
result Reservoir Memory Machines solve benchmark tasks as well as Neural Turing Machines but are much faster to train.
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.
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.
Neural Turing Machines (NTMs) are an instance of Memory Augmented Neural Networks, a new class of recurrent neural networks which decouple computation from memory by introducing an external memory unit. NTMs have demonstrated superior performance over Long Short-Term Memory Cells in several sequence learning tasks. A n…
NeuZip compresses neural network weights to save memory during training and inference.
problem Memory constraints in neural network training and inference.
method Entropy-based dynamic weight compression.
result Significant reduction in memory usage without performance loss.
Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Networkeess.AS
Paper proposes low-rank gradient approximation to save memory for deep neural network training.
problem Memory limitation on mobile devices for deep neural network training.
method Approximating gradient matrices using low-rank parameterization.
result Reduces training memory by about 33.0% for Adam optimization and 4.5% relative lower word error rate on ASR personalization task.
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…
Proposes a plastic neural memory model for better anomaly detection.
problem Static attention mechanisms limit NMNs in anomaly detection.
method Introduces dynamic connection weights for improved knowledge retrieval.
result Outperforms state-of-the-art in three medical anomaly detection tasks.
Proposes a novel SAM operator for separate item and relational memories.
problem Limited memory interactions in neural networks.
method Introduces a Self-attentive Associative Memory (SAM) operator to separate item and relational memories.
result Achieves competitive results in various tasks, including geometry, graph, reinforcement learning, and question answering.
Memory-augmented neural networks (MANNs) have been shown to outperform other recurrent neural network architectures on a series of artificial sequence learning tasks, yet they have had limited application to real-world tasks. We evaluate direct application of Neural Turing Machines (NTM) and Differentiable Neural Compu…
Efficient echo state network with explicit memory performs well on benchmark tasks.
problem Training differentiable neural computers is difficult and time-consuming.
method Echo state network with an explicit memory.
result Echo state network can recognize all regular languages, including those contractive networks cannot.
NANSDE-Net models time series with memory using neural ARMA-type noise.
problem Modeling time series with long- or short-memory characteristics.
method Developed NANSDE-Net, a generative model that incorporates Neural Network-kernel ARMA-type noise.
result NANSDE-Net matches or outperforms existing models in reproducing long- and short-memory features of data.
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…
Researchers save memory on MCUs by reordering neural network operators.
problem Memory constraints on microcontrollers for neural network inference.
method Operator reordering to save memory, orthogonal to other compression methods.
result Reduced memory footprint of a CNN to deploy on an MCU with 512KB SRAM.
SMGD trains low-bit neural networks with memory constraints.
problem Training large neural networks with limited memory.
method Stochastic Markov Gradient Descent (SMGD).
result Encouraging numerical results and theoretical guarantees.
Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled. We introduce a novel recurrent architecture based on the conceptual separation b…
Model combines long-term and short-term memory using conceptors.
problem Transfer between long-term and short-term memory.
method Recurrent neural network with gated reservoir for short-term memory and conceptors for long-term memory.
result Standard operations on conceptors allow combining long-term memories and describing their effect on short-term memory.
Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use residual, parallel structures and concatenation block between shallow and deep features …
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…
Deep neural networks with memory learn reduced equations from partial data.
problem Constructing governing equations for unknown dynamical systems from limited data.
method Formulate a discrete approximation of memory integrals, use deep neural networks to incorporate history terms.
result Deep neural networks can learn reduced equations with memory from partial data.
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.
Generative diffusion models mimic biological memory networks, encoding associative dynamics in deep neural weights.
problem Understanding long-term memory mechanisms in neuroscience and AI.
method Interpreting generative diffusion models as energy-based models and comparing them to Hopfield networks.
result Generative diffusion models can encode associative dynamics of Hopfield networks in deep neural weights.
Tree-SMU enables strong compositional generalization in neural networks.
problem Zero-shot generalization to novel compositions of concepts.
method Tree Stack Memory Units (Tree-SMU) with Stack Memory Units (SMU).
result Tree-SMU achieves strong empirical results on mathematical reasoning benchmarks.
The Unlearning algorithm improves neural network performance in memory tasks.
problem Improving neural network performance in memory tasks.
method Simplified Unlearning algorithm, structured training data, and new regularization technique for Boltzmann Machines.
result The Unlearning rule outperforms traditional Boltzmann-Machine learning in learning hidden probability distributions.
Efficient memory layer improves graph neural networks for graph classification and regression.
problem Efficiently learning node representations and graph coarsening for arbitrary graph topology.
method Introduces a memory layer for GNNs that learns node representations and graph coarsening, and two new networks: MemGNN and GMN.
result Proposed models achieve state-of-the-art results in graph classification and regression benchmarks.
Study proposes memory-efficient backpropagation for linear layers in neural networks.
problem Significant memory usage in backpropagation through linear layers in neural networks.
method Randomized matrix multiplications to reduce memory usage with a moderate decrease in test accuracy.
result Demonstrated benefits of the proposed method on fine-tuning pre-trained models.
Explosive neural networks via higher-order interactions in curved statistical manifoldscond-mat.dis-nn
New neural networks model complex phenomena with fewer parameters.
problem Challenges in studying higher-order interactions in neural networks.
method Introducing curved neural networks using the maximum entropy principle.
result Curved neural networks accelerate memory retrieval and exhibit explosive phase transitions.
Neural SVEs model complex systems with memory, outperforming traditional methods.
problem Modeling systems with memory effects and irregular behavior.
method Introducing neural stochastic Volterra equations as a physics-inspired architecture.
result Neural SVEs outperform neural SDEs and DeepONets in various applications.
New neural operators model turbulence with memory and randomness.
problem Modeling turbulence in complex fluid dynamics with memory and randomness.
method Symmetrized activation functions, fractional derivatives, and stochastic noise.
result Theoretical guarantees for approximation quality in turbulent phenomena.
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…
Recurrent Neural Networks with more flexible memory: better predictions than rough volatilityq-fin.ST
Extended LSTMs improve volatility prediction by 20%.
problem Predicting asset price volatility with long memory.
method Extended LSTMs with multiple flexible timescales.
result Extended LSTMs outperform rough volatility predictions by 20%.
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.
Memory is increasingly often the bottleneck when training neural network models. Despite this, techniques to lower the overall memory requirements of training have been less widely studied compared to the extensive literature on reducing the memory requirements of inference. In this paper we study a fundamental questio…
Machine-assisted treatment recommendations hold a promise to reduce physician time and decision errors. We formulate the task as a sequence-to-sequence prediction model that takes the entire time-ordered medical history as input, and predicts a sequence of future clinical procedures and medications. It is built on the …
Learning to remember long sequences remains a challenging task for recurrent neural networks. Register memory and attention mechanisms were both proposed to resolve the issue with either high computational cost to retain memory differentiability, or by discounting the RNN representation learning towards encoding shorte…
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…
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.
This paper reviews methods to create compact neural networks for IoT applications.
problem Complex deep neural networks are costly and slow, hindering real-world deployment.
method Automatic synthesis of compact, accurate DNN/LSTM models.
result Compact neural networks reduce energy consumption, memory, and inference time.
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.
ActNN reduces neural network training memory by 2-bit quantization.
problem Limited memory in training neural networks.
method Randomly quantizes activations to 2 bits, proving convergence and proposing mixed-precision strategies.
result Reduces activation memory footprint by 12x with negligible accuracy loss.
Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory Networkscs.CV
HMN detects fake faces using memory networks and visual cues.
problem Detecting fake faces from unseen manipulation types.
method Hierarchical Memory Network (HMN) architecture.
result Superior performance in fake and fraudulent face detection.
Neural memory networks improve seizure type classification.
problem Automating the classification of seizure type for clinical and research purposes.
method Introduced a novel approach using neural memory networks (NMNs) enhanced with external memory modules and trainable neural plasticity.
result Achieved a state-of-the-art weighted F1 score of 0.945 for seizure type classification.
Enhances sequence memory capacity in neural networks.
problem Limited sequence capacity in Hopfield-like neural networks.
method Introducing a nonlinear interaction term and a generalized pseudoinverse rule.
result Significantly increased sequence capacity with novel scaling laws.
New kernel-based models improve on traditional neural methods in sequence modeling.
problem Sequence modeling challenges in natural language processing and neuroscience.
method Kernel-based recurrent neural networks and convolutional neural networks.
result Kernel-based models perform on par or better than traditional neural methods.
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…