V-HMN integrates memory mechanisms for improved image recognition.
problem Limited interpretability and high data requirements of existing vision backbones.
method Brain-inspired hierarchical memory modules with iterative refinement.
result V-HMN achieves strong performance on image classification benchmarks.
STanHop predicts multivariate time series with memory-enhanced capabilities.
problem Predicting multivariate time series with memory-enhanced capabilities.
method Sparse Tandem Hopfield Network (STanHop) with two external memory modules.
result STanHop outperforms dense Hopfield models in memory retrieval error.
The ability to generalize quickly from few observations is crucial for intelligent systems. In this paper we introduce APL, an algorithm that approximates probability distributions by remembering the most surprising observations it has encountered. These past observations are recalled from an external memory module and…
We propose a new architecture called Memory-Augmented Encoder-Solver (MAES) that enables transfer learning to solve complex working memory tasks adapted from cognitive psychology. It uses dual recurrent neural network controllers, inside the encoder and solver, respectively, that interface with a shared memory module a…
Proposes ContSup to boost local learning by supplying context between isolated modules.
problem Local learning's performance degrades with more isolated modules.
method Theoretical analysis and ContSup scheme to supply context between modules.
result Significant performance improvement with minimal overhead.
Improved recurrent neural networks learn long-term dependencies through multi-scale memory.
problem Capturing long-term dependencies in recurrent neural networks.
method Incremental training of a modular RNN architecture with multi-scale hidden states.
result Incremental training and multi-scale memory enhance RNNs' ability to learn long-term dependencies.
This paper proposes an alternative to E2E training for deep networks, reducing memory footprint.
problem High GPUs memory footprint in end-to-end training of deep networks.
method Locally supervised learning with information propagation loss to avoid information collapse.
result The proposed method achieves competitive performance with less than 40% memory footprint compared to E2E training.
When analyzing the genome, researchers have discovered that proteins bind to DNA based on certain patterns of the DNA sequence known as "motifs". However, it is difficult to manually construct motifs due to their complexity. Recently, externally learned memory models have proven to be effective methods for reasoning ov…
This paper proposes a new approach to Transformers by integrating hierarchical associative memory with MetaFormers.
problem Theoretical framework for Transformers and MLP-Mixers remains underdeveloped.
method Integrating hierarchical associative memory with MetaFormers to create a parallelized MLP-Mixer.
result Symmetry-breaking effects improve the performance of the MLP-Mixer in image recognition tasks.
Adaptive Quantization Modules enable online continual compression of non-i.i.d data streams.
problem Learning to compress and store a dataset from a non-i.i.d data stream, only observing each sample once.
method Discrete auto-encoders and Adaptive Quantization Modules (AQM) to control compression ability.
result Significant gains on continual learning benchmarks with AQM replacing episodic memory.
StageNet improves health risk prediction by integrating disease stage information.
problem Improving health risk prediction for patients with chronic conditions.
method StageNet uses a stage-aware LSTM and stage-adaptive convolutional modules to extract and integrate disease stage information.
result StageNet achieves up to 12% higher AUPRC for risk prediction and over 58% higher Calinski-Harabasz score for patient subtyping compared to state-of-the-art models.
KM method reduces ConvNet parameters to 9% higher accuracy with minimal additional memory.
problem Expensive memory usage for training ConvNets on embedded devices.
method Kernel Modulation (KM) method that adapts all network parameters for each task.
result KM delivers up to 9% higher accuracy than other parameter-efficient methods.
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.
NoNN compresses deep networks into distributed IoT modules with minimal communication.
problem Memory and communication constraints in IoT devices for deep learning inference.
method NoNN compresses a large pretrained network into disjoint, highly-compressed student modules, optimizing for memory and communication.
result NoNN achieves higher accuracy than baselines and similar to the teacher model with minimal communication.
This paper presents a novel framework for predicting shot location and type in tennis. Inspired by recent neuroscience discoveries we incorporate neural memory modules to model the episodic and semantic memory components of a tennis player. We propose a Semi Supervised Generative Adversarial Network architecture that c…
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.
Model learns continuously from text without forgetting.
problem Catastrophic forgetting in lifelong language learning.
method Episodic memory with sparse experience replay and local adaptation.
result Model can continuously learn from new datasets.
Spectrum selectively trains LLMs based on SNR to save resources.
problem Efficiently training large language models with limited resources.
method Targeting layer modules based on SNR for selective training.
result Spectrum achieves similar performance to full fine-tuning but with reduced VRAM usage.
Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods. It is unclear, however, whether they also have an ability to perform complex relational reasoning with the information they remember. Here, we first confirm our intuitions that standard memory architectur…
FinMem enhances LLM trading agents with layered memory and character design.
problem Developing purpose-driven LLM agents for financial decision-making.
method Integrates layered memory and character design modules into an LLM framework.
result Significantly enhanced trading performance in financial markets.
Proposes TEMN for better POI recommendations.
problem Challenges in capturing user preferences and spatio-temporal POI relationships.
method Integrates topic model and memory network, incorporating geographical module.
result Improves POI recommendation effectiveness by 3.25% and 29.95%.
The paper explores how gradient descent trains associative memories, revealing oscillations and convergence issues.
problem Training dynamics of associative memories in overparameterized and underparameterized settings.
method Reduction to particle system dynamics, theory, and experiments.
result Oscillatory transitory regimes and benign loss spikes in overparameterized settings, suboptimal memorization in underparameterized settings.
Silas provides transparent, verifiable machine learning models.
problem Creating reliable and explainable machine learning models.
method Formal verification, correct training, and transparent reasoning modules.
result Silas models are formally verified and correct.
New model adds persistent memory to self-attention layers for improved performance.
problem Improving transformer performance by removing feed-forward layers.
method Augmenting self-attention layers with persistent memory vectors.
result The model outperforms standard transformers on language modeling benchmarks.
A new model improves recurrent neural networks' ability to memorize long sequences.
problem Improving recurrent neural networks' ability to memorize long sequences and extract task-relevant features.
method Proposes a Linear Memory Network with an encoding-based memorization component and a specialized training algorithm.
result Improves the final performance of recurrent neural networks when memorizing long sequences is necessary.
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.
Paper extends Lévy models with memory to better price FX double barrier options.
problem Efficiently pricing double barrier options in complex FX models.
method Introduces regime-switching Lévy models with memory and a modified numerical method.
result New models and method improve accuracy of option pricing.
We first pose the Unsupervised Progressive Learning (UPL) problem: an online representation learning problem in which the learner observes a non-stationary and unlabeled data stream, learning a growing number of features that persist over time even though the data is not stored or replayed. To solve the UPL problem we …
PLoP optimizes LoRA placement for efficient large model finetuning.
problem Improving efficiency of LoRA adaptation for large models.
method Intuitive theoretical analysis for automatic adapter placement.
result PLoP consistently outperforms existing placement strategies.
NIPA aims to translate brain learning mechanisms into scalable Bayesian inference.
problem Scalable Bayesian inference for large-scale statistical machine learning problems.
method Neural-inspired algorithm combining model-based, model-free, and episodic-control modules.
result Advances Bayesian methods and facilitates their application to deep learning.
Comprehending complex systems by simplifying and highlighting important dynamical patterns requires modeling and mapping higher-order network flows. However, complex systems come in many forms and demand a range of representations, including memory and multilayer networks, which in turn call for versatile community-det…
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 …
RSAC improves lightweight continuous learning efficiency.
problem Excessive training time and memory usage in continuous learning.
method Regularized subspace approximation classifier with feature reduction and regularization.
result RSAC achieves more efficient continuous learning than prior methods.
New approach tackles open compound domain adaptation without clear domain labels.
problem Adapting models to new, mixed domains without domain labels.
method Curriculum domain adaptation strategy and memory module.
result Demonstrated effectiveness on various tasks.
Recent progress in deep learning is revolutionizing the healthcare domain including providing solutions to medication recommendations, especially recommending medication combination for patients with complex health conditions. Existing approaches either do not customize based on patient health history, or ignore existi…
This paper proposes an attention module augmented relational network called SARN(Sequential Attention Relational Network) that can carry out relational reasoning by extracting reference objects and making efficient pairing between objects. SARN greatly reduces the computational and memory requirements of the relational…
Unified perspective on Hopfield networks with attention module.
problem Understanding and optimizing Hopfield networks with attention mechanisms.
method Study of BM counterparts of modern Hopfield networks and their salient properties.
result Introduction of AttnBM with tractable likelihood and gradient.
Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional, long short-term memory (convLSTM) modules. We introduce a novel reduced-gate convolutional LSTM(rgcLSTM) architecture that…
Machine reading using differentiable reasoning models has recently shown remarkable progress. In this context, End-to-End trainable Memory Networks, MemN2N, have demonstrated promising performance on simple natural language based reasoning tasks such as factual reasoning and basic deduction. However, other tasks, namel…
Deep learning compresses L-values for QAM symbols, reducing memory and improving performance.
problem Efficiently storing log-likelihood ratios (L-values) for QAM modulation.
method A deep autoencoder that jointly compresses and reconstructs L-values with a weighted loss function.
result Reduces memory footprint by up to two times with less than 0.1 dB performance loss.
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.
TGNs learn from dynamic graphs efficiently and outperform previous methods.
problem Learning from graphs that evolve over time.
method Temporal Graph Networks (TGNs) combining memory and graph operators.
result Significantly outperforms previous approaches on dynamic graphs.
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 …
Despite recent advances, large scale visual artifacts are still a common occurrence in images generated by GANs. Previous work has focused on improving the generator's capability to accurately imitate the data distribution pdata. In this paper, we instead explore methods that enable GANs to actively avoid errors b…
New schemes improve lifelong learning by balancing old and new tasks.
problem Catastrophic forgetting in deep neural networks when learning multiple tasks.
method Unified optimization perspective of episodic memory based approaches, introducing MEGA-I and MEGA-II schemes.
result Significant improvement in lifelong learning benchmarks, reducing error by up to 18%.
Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the accumulation, deformation or dissipation of radar echoes in precipitation forecasting. Fr…
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…
LSTM neural networks improve fiber nonlinearities in coherent systems.
problem Compensating fiber nonlinearities in digital coherent systems.
method Utilization of Long short-term memory (LSTM) neural networks.
result LSTM neural networks provide superior performance compared to digital back propagation, especially in multi-channel scenarios.