We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories ar…
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
48 results for “semantic memory”
Paper develops rules for autonomous driving using semantic memory.
problem Creating rules for autonomous driving systems.
method Uses real driving data and semantic memory for rule learning.
result Automatic rule learning for autonomous driving.
Tensor models decode human perception and memory using SPO triples.
problem Understanding implicit and explicit perception and memory in the brain.
method Tensor models with SPO triples, dual representations, and four layers.
result Semantic memory is crucial for explicit perception and declarative memories.
Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memorycs.NE
New memory allocation scheme improves image generation performance.
problem Improving episodic and semantic memory representation in neural networks.
method Developed a hierarchical latent variable model with differentiable, locally block allocated latent memory.
result Improved conditional likelihood values on various datasets.
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…
HawkesLLM models text generation with temporal influence, improving semantic alignment under limited memory.
problem Path-dependent uncertainty in agentic text-simulation systems.
method HawkesLLM framework separates temporal influence modeling from text generation, using a multivariate Hawkes process and a language model.
result HawkesLLM improves late-stage semantic alignment under a compact prompt-memory budget.
METEOR learns efficient representations from multi-modal data streams.
problem Efficiently interpreting multi-modal information in complex environments.
method METEOR learns compact representations by sharing parameters within semantically meaningful groups and preserving domain-agnostic semantics.
result METEOR reduces memory usage by around 80% compared to conventional methods.
Intelligence emerges from stabilizing invariant cycles in memory.
problem Understanding the nature of intelligence and its emergence.
method Structural-dynamical account rooted in a topological closure law: \(\partial^2=0\).
result Memory-amortized inference (MAI) mechanism that implements SbS \(
ightarrow\) CCUP.
Innovative neural networks reduce memory usage for efficient, accurate segmentation.
problem Efficiently segmenting large graphs with limited memory.
method Iterative neural networks with loops and multiple outputs.
result State-of-the-art semantic segmentation results on demanding datasets.
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.
Two GPU memory management approaches reduce deep learning model memory usage.
problem Limited GPU memory in deep learning systems.
method Two orthogonal approaches exploiting iterative training algorithm to optimize memory usage.
result Up to 34.2% reduction in memory usage without communication overhead.
We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate. MAPO is applicable to deterministic environments with discrete actions, such as structured prediction and combinatorial optimization ta…
Method tackles catastrophic forgetting in CNNs for remote sensing data.
problem Catastrophic forgetting in CNNs when adding new classes without old class annotations.
method Incremental learning approach using a frozen network as memory and a loss function balancing new and old classes.
result Performance for old classes maintained while adding new classes, without old class annotations.
LatticeNet segments 3D point clouds faster and more efficiently.
problem Challenges in applying CNNs to 3D point cloud data.
method Embeds point cloud geometry into a permutohedral lattice for fast convolutions.
result Achieves state-of-the-art performance in 3D segmentation.
Memory-enhanced model predicts tennis shots based on player history.
problem Predicting shot location and type in tennis.
method Semi-supervised Generative Adversarial Network with neural memory modules.
result The model learns player-specific behavioral patterns from match data.
DVNet efficiently segments large neurovascular datasets using skip connections.
problem Challenges in segmenting large neurovascular datasets from high-throughput microscopy data.
method A fully-convolutional, deep, and densely-connected encoder-decoder network with skip connections.
result DVNet achieves superior performance in semantic segmentation of neurovascular datasets.
PipeDream-2BW accelerates large model training by 20x with minimal memory usage.
problem Training large models requires memory beyond single accelerator capacity.
method Pipeline parallelism, weight gradient coalescing, double buffering.
result Accelerates large model training by up to 20x.
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.
Improved text summarization using neural semantic encoders with hierarchical structure.
problem Capturing long-term dependencies in text summarization.
method Proposed a novel hierarchical Neural Semantic Encoder (NSE) model augmented with lemma and PoS tags.
result Significantly outperformed state-of-the-art models in ROUGE metric.
Paper develops a framework for generating coherent image captions using visual features and hierarchical topics.
problem Generating semantically coherent paragraphs to describe image content.
method Plug-and-play hierarchical-topic-guided image paragraph generation framework integrating visual extractor and deep topic model.
result Proposed models can distill interpretable multi-layer semantic topics and generate diverse and coherent captions.
A novel memory mechanism for reinforcement learning agents that stores past events in human-readable language.
problem Lack of interpretability in reinforcement learning agent's memory mechanisms.
method Uses CLIP to associate visual inputs with language tokens, then feeds these tokens to a pretrained language model.
result Significantly faster convergence on challenging continuous recognition tasks.
Study improves semantic segmentation of LiDAR point clouds for autonomous vehicles.
problem Semantic understanding of 3D LiDAR data for autonomous vehicles.
method Image-based semantic segmentation architectures, network size optimization, improved point cloud projection, soft Dice loss, reduced weight-sharing convolution.
result 3.2% increase in mIoU segmentation performance with 42% reduction in inference time.
Hypothesis testing is an important cognitive process that supports human reasoning. In this paper, we introduce a computational hypothesis testing approach based on memory augmented neural networks. Our approach involves a hypothesis testing loop that reconsiders and progressively refines a previously formed hypothesis…
MDEQ models learn multi-resolution features efficiently.
problem Large-scale, hierarchical pattern recognition.
method Implicit differentiation, multiscale deep equilibrium model.
result MDEQs achieve performance on par with recent models.
Efficient Discrete Supervised Hashing improves cross-modal retrieval by preserving semantic correlations and reducing quantization error.
problem Challenges in preserving semantic correlations and reducing quantization error in cross-modal hashing for large-scale retrieval.
method Collective matrix factorization on heterogenous features and semantic embedding with class labels to learn hash codes efficiently.
result EDSH produces superior performance in both accuracy and scalability over existing methods.
The abstract explains how word and relation representations capture semantic meaning.
problem Understanding how word and relation representations capture semantic meaning.
method Theoretical justification and extension of geometric relationships between word embeddings and knowledge graph representations.
result The geometric relationships between word embeddings correspond to semantic relations between words and entities in knowledge graphs.
Recurrent neural networks (RNNs) have been drawing much attention with great success in many applications like speech recognition and neural machine translation. Long short-term memory (LSTM) is one of the most popular RNN units in deep learning applications. LSTM transforms the input and the previous hidden states to …
In the current context of data explosion, online techniques that do not require storing all data in memory are indispensable to routinely perform tasks like principal component analysis (PCA). Recursive algorithms that update the PCA with each new observation have been studied in various fields of research and found wi…
Enhances hashing for fast retrieval with correlated bits.
problem Fast retrieval and small memory footprint for large-scale information retrieval.
method Employing Boltzmann machine distribution as variational posterior to model correlations among hash code bits.
result Significant performance gains achieved by effectively modeling correlations among hash code bits.
Fundamental Limits of Online and Distributed Algorithms for Statistical Learning and Estimationcs.LG
Many machine learning approaches are characterized by information constraints on how they interact with the training data. These include memory and sequential access constraints (e.g. fast first-order methods to solve stochastic optimization problems); communication constraints (e.g. distributed learning); partial acce…
DPQ offers significant compression at minimal cost for embedding layers.
problem Memory and storage constraints in embedding layers.
method Differentiable Product Quantization (DPQ) framework with two instantiations.
result Significant compression ratios (14-238) with negligible performance cost.
Efficient BNNs learn latent distributions for robust uncertainty quantification.
problem Improving robustness and uncertainty of deep neural networks.
method LP-BNN uses VAEs to learn latent distributions of BNN parameters, enabling efficient ensembles.
result LP-BNN achieves competitive results in image classification, semantic segmentation, and out-of-distribution detection.
A new perspective on self-attention models using MLPs.
problem Improving sequence modeling with self-attention mechanisms.
method Introducing HyperMLP and HyperGLU, which use dynamic two-layer MLPs with reverse-offset layout.
result HyperMLP/HyperGLU consistently outperform softmax-attention baselines.
While accelerators such as GPUs have limited memory, deep neural networks are becoming larger and will not fit with the memory limitation of accelerators for training. We propose an approach to tackle this problem by rewriting the computational graph of a neural network, in which swap-out and swap-in operations are ins…
Fruit fly brain network learns word embeddings using sparse binary codes.
problem Learning semantic word representations from text.
method Inspired by mushroom body neural network, sparse binary hash codes.
result Fruit fly network achieves comparable NLP performance with reduced resources.
Paper forecasts commodity price spikes using AI and economic news.
problem Accurate forecasting of commodity price spikes for economic stability.
method Hybrid framework combining historical data and semantic signals from economic news.
result Model achieves high AUC and accuracy in detecting price shocks.
Action recognition has attracted increasing attention from RGB input in computer vision partially due to potential applications on somatic simulation and statistics of sport such as virtual tennis game and tennis techniques and tactics analysis by video. Recently, deep learning based methods have achieved promising per…
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we employ deconvolutional networks as the sequence decoder (generator), providing l…
Enhanced portfolio selection using sentiment data and LSTM.
problem Improving portfolio selection through sentiment analysis and price prediction.
method Semantic Attention Model for sentiment prediction, LSTM for price prediction, mean-variance strategy for portfolio optimization.
result Sentiment-aware portfolio strategies outperform non-sentiment aware models on average.
Entity linking is the task of mapping potentially ambiguous terms in text to their constituent entities in a knowledge base like Wikipedia. This is useful for organizing content, extracting structured data from textual documents, and in machine learning relevance applications like semantic search, knowledge graph const…
In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a densely connected spatio-temporal graph by capitalizing on recent advances on deep Gaussian Conditional …
Deep neural networks (DNN) trained in a supervised way suffer from two known problems. First, the minima of the objective function used in learning correspond to data points (also known as rubbish examples or fooling images) that lack semantic similarity with the training data. Second, a clean input can be changed by a…
Improved autoencoder boosts sequence learning with less memory.
problem Training recurrent networks with high memory costs.
method Sparse Predictive Autoencoder (bRSM) with recurrent connections and boosting rule.
result Near optimal performance on stochastic sequence learning task.
NVIDIA cuDNN is a low-level library that provides GPU kernels frequently used in deep learning. Specifically, cuDNN implements several equivalent convolution algorithms, whose performance and memory footprint may vary considerably, depending on the layer dimensions. When an algorithm is automatically selected by cuDNN,…
An Efficient Shared-memory Parallel Sinkhorn-Knopp Algorithm to Compute the Word Mover's Distancecs.LG
This paper speeds up WMD computation for multiple queries efficiently.
problem Efficiently computing the semantic dissimilarity between text documents.
method Adapting the Sinkhorn-Knopp algorithm to compute WMD of one document against many targets in parallel.
result 67x speedup on 96 cores compared to sequential and naive parallel methods.
Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.
problem Challenges in handling semantic and hierarchical structure in knowledge areas.
method Introduces a novel learner model that exploits semantic relatedness between knowledge components using a Wikipedia link graph.
result Achieves statistically significant improvements in predictive performance for educational engagement.
Binary representation is desirable for its memory efficiency, computation speed and robustness. In this paper, we propose adjustable bounded rectifiers to learn binary representations for deep neural networks. While hard constraining representations across layers to be binary makes training unreasonably difficult, we s…
Automated translation of mathematical formulae using recursive neural networks.
problem Performing translations between different representations of mathematical formulae.
method Recursive neural networks with multi-variate multi-valued Long Short-Term Memory cells and novel clustering and mini-batch training techniques.
result Achieved a prediction accuracy of 47.05% for predicting symbols at the correct position and 92.3% when ignoring the predicted position.