Neural Module Networks, originally proposed for the task of visual question answering, are a class of neural network architectures that involve human-specified neural modules, each designed for a specific form of reasoning. In current formulations of such networks only the parameters of the neural modules and/or the or…
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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “neural modules”
Paper presents a novel neural network for MIMO symbol detection.
problem Handling a variable number of users in MIMO systems.
method Recurrent and permutation equivariant neural network architecture with iterative decoding.
result The neural detector outperforms existing methods in accuracy and efficiency.
MoNODEs improve neural ODEs by separating dynamic states from static factors.
problem Learning non-linear dynamics with variations across trajectories.
method Introduces time-invariant modulator variables to separate dynamic states from static factors.
result Consistently improves model generalization and far-horizon forecasting.
Light neural network detects modulation in noisy signals.
problem Efficiently detecting modulation in noisy signals.
method Light neural network architecture invariant to impairments.
result Network achieves accuracy under realistic impairments.
Two solutions for multi-modal record linkage using Deep Learning inspired by Visual Question Answering.
problem Matching records from multiple sources representing the same entity.
method Two fusion modules: Recurrent Neural Network + Convolutional Neural Network and Stacked Attention Network. A Siamese Neural Network computes similarity.
result Recurrent Neural Network + Convolutional Neural Network fusion module outperforms a simple model.
We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution. Given an input, only a subset of D2NN neurons are executed, and the particular subset is determined by the D2NN itself. By pruning unnecessary computation depending on input, D2NNs provide a…
We propose a novel deep learning method for local self-supervised representation learning that does not require labels nor end-to-end backpropagation but exploits the natural order in data instead. Inspired by the observation that biological neural networks appear to learn without backpropagating a global error signal,…
Proposes Fusion Recurrent Neural Network for sequence data.
problem Improving sequence learning for practical applications.
method Fusion module and Transport module for sequence data.
result Fusion RNN performs comparably to state-of-the-art RNNs.
NFM improves deep learning by selectively processing hidden states.
problem Processing entire hidden states in each layer limits modularity and reusability.
method Introduces Neural Function Modules (NFM) with attention, sparsity, and feedback.
result Improves results in classification, generalization, generative modeling, and reinforcement learning.
COIN++ compresses multiple data types efficiently.
problem Handling diverse data modalities in neural compression.
method Implicit neural representations and modulations quantization.
result Significant compression gains with reduced encoding time.
Learn to automatically plug domain-specific modules into a common network.
problem Learning inflexibility and computational intensiveness in multi-domain learning.
method Neural Architecture Search (NAS) for data-driven adapter plugging and structure design.
result NAS-driven MDL model achieves comparable performance to existing approaches.
A new neural network captures and explains trajectory patterns.
problem Analyzing complex spatial trajectories in urban planning and neuroscience.
method Composite Signal Neural Networks (CompSNN) combining three interpretable ANN modules.
result CompSNN outperforms individual modules and visualizes useful signal parts.
Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number of parameters with a relatively small increase in resources. We propose a train…
Shared workspace improves neural module coordination in deep learning.
problem Pairwise interactions in deep learning models lack global coordination.
method Introduce a shared global workspace with bandwidth limitations among neural modules.
result Capacity limitations encourage specialization and synchronization.
Paper tackles division difficulty, proposing new methods to improve accuracy.
problem Division is the most challenging arithmetic operation for both humans and computers.
method Proposes two novel approaches: Neural Reciprocal Unit (NRU) and Neural Multiplicative Reciprocal Unit (NMRU), and improves an existing division module.
result Improves division accuracy from 70.2% to 91.6%.
NACs learn modular neural architectures without domain knowledge.
problem Jointly learn module configuration and execution without domain knowledge.
method Jointly trains two systems: module configuration and execution.
result Improves low-shot adaptation and OOD robustness.
We study the phenomenon that some modules of deep neural networks (DNNs) are more critical than others. Meaning that rewinding their parameter values back to initialization, while keeping other modules fixed at the trained parameters, results in a large drop in the network's performance. Our analysis reveals interestin…
Improved neural ODEs learn adaptable flows.
problem Neural ODEs struggle with expressive power and adaptability.
method Introduce N-CODE modules with dynamic parameters controlled by a trainable map.
result N-CODE modules enhance expressivity of neural ODEs.
Graph Neural Network (GNN) is a popular architecture for the analysis of chemical molecules, and it has numerous applications in material and medicinal science. Current lines of GNNs developed for molecular analysis, however, do not fit well on the training set, and their performance does not scale well with the comple…
A deep learning subsampling technique improves modulation classification accuracy.
problem Improving modulation classification accuracy in wireless communication systems.
method Proposes a data-driven subsampling strategy using deep neural networks to simulate signal removal.
result Improves classification accuracy to higher levels than traditional methods.
Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial intelligent systems. However, neural networks suffer from catastrophic forgetting when…
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.
In this work, we investigate the value of employing deep learning for the task of wireless signal modulation recognition. Recently in [1], a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections in a real wireless channel, and uses 10 different modulation types. Further, a …
Differentiable Window improves attention modules by enabling more focused attentions.
problem Improving attention mechanisms in neural networks.
method Proposes Differentiable Window, a neural module for dynamic window selection.
result Consistent and sizable improvements across various NLP tasks.
Tensor decomposition methods are widely used for model compression and fast inference in convolutional neural networks (CNNs). Although many decompositions are conceivable, only CP decomposition and a few others have been applied in practice, and no extensive comparisons have been made between available methods. Previo…
Paper investigates Lipschitz constants of self-attention modules in neural networks.
problem Lipschitz constants of self-attention modules in neural networks.
method Proved standard dot-product self-attention is not Lipschitz for unbounded input domain. Proposed L2 self-attention that is Lipschitz. Derived upper bound on L2 self-attention's Lipschitz constant.
result Proved standard self-attention is not Lipschitz for unbounded input domain and proposed an alternative L2 self-attention that is Lipschitz.
A training-free message passing module improves hypergraph neural networks.
problem Computational intensive training process in hypergraph neural networks.
method Decoupling hypergraph structural information from model learning stage.
result TF-HNN achieves superior performance and training efficiency.
Pyramid Attention Networks improve image restoration by leveraging self-similarities across scales.
problem Lack of full exploitation of self-similarities in image restoration by recent deep learning methods.
method Introduces a Pyramid Attention module that processes multi-scale feature correspondences to borrow clean signals from coarser levels.
result Pyramid Attention module achieves state-of-the-art results in various image restoration tasks.
A new GNN module learns geometric scattering features for better graph classification and feature exploration.
problem Learning long-range graph relations and extracting meaningful features from graphs.
method Proposes a learnable geometric scattering (LEGS) module in graph neural networks (GNNs), incorporating wavelet filters.
result LEGS-based GNNs outperform existing methods in graph classification and feature extraction tasks.
Paper proposes a time-frequency analysis method for blind modulation classification in MIMO systems.
problem Blind modulation classification in MIMO systems with overlapping signals and unknown channel parameters.
method Time-frequency analysis using windowed short-time Fourier transform, conversion to RGB spectrogram images, convolutional neural network for classification, decision fusion.
result Proposed scheme achieves high classification accuracy at different SNRs, outperforming existing methods.
The principles of adaptation in organisms and machines II: Thermodynamics of the Bayesian brainq-bio.NC
The article explores how organisms and machines learn and recognize the world using Bayesian inference and thermodynamics.
problem Understanding how organisms and machines learn and recognize the world.
method Introducing a thermodynamic view of the Bayesian brain hypothesis, using a simple generative model of spiking neural populations.
result The process of Bayesian inference can be quantified using entropy, revealing the perceptual capacity of neural activity.
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.
Spatio-temporal (ST) data, which represent multiple time series data corresponding to different spatial locations, are ubiquitous in real-world dynamic systems, such as air quality readings. Forecasting over ST data is of great importance but challenging as it is affected by many complex factors, including spatial char…
This research explores complex-valued neural networks and their implementation.
problem The challenges of implementing complex-valued neural networks and their potential for non-complex data.
method Detailed theory and implementation of CVNN, including Wirtinger calculus, complex backpropagation, and modules like complex layers and activation functions. Python implementation using cvnn toolbox.
result Demonstrates the potential of CVNN for non-complex data through simulations.
Improved neural networks for relational reasoning by projecting high-dimensional data to low-dimensional manifolds.
problem Out-of-distribution generalization in complex relational reasoning tasks.
method Neuroscience-inspired inductive-biased module projecting high-dimensional object representations to low-dimensional manifolds.
result Significantly better out-of-distribution generalization performance on relational reasoning tasks.
Shape adaptor learns flexible resizing factors for neural networks.
problem Fixed resizing layers limit network performance.
method Learnable reshaping factor for traditional resizing layers.
result Performance increases consistently across multiple datasets.
E2GC optimizes energy efficiency in DNNs by balancing computational and data movement costs.
problem Imbalance between computational complexity and data reuse in GConv leads to suboptimal energy efficiency.
method Developed an optimum group size model and proposed E2GC module with constant group size.
result E2GC modules improve energy efficiency by 10.8% and 4.73% on P100 and P4000 GPUs, respectively.
PICLE uses probabilistic models to efficiently evaluate and compose modules for continual learning.
problem Challenging search space of module compositions in continual learning.
method Probabilistic framework to cheaply compute module compositions' fitness.
result First modular CL algorithm to achieve perceptual, few-shot, and latent transfer.
Deep Forestcs.LG
Current deep learning models are mostly build upon neural networks, i.e., multiple layers of parameterized differentiable nonlinear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules. We conjecture that the mystery behind…
The study of neurocognitive tasks requiring accurate localisation of activity often rely on functional Magnetic Resonance Imaging, a widely adopted technique that makes use of a pipeline of data processing modules, each involving a variety of parameters. These parameters are frequently set according to the local goal o…
Extends hyperparameter transfer across model sizes and modules, improving training speed.
problem Training stability and performance of large-scale models with optimal hyperparameters.
method Complete Parameterisation, per-module hyperparameter optimisation and transfer.
result Hyperparameter transfer holds even in the per-module hyperparameter regime, improving training speed.
The deep learning trend has recently impacted a variety of fields, including communication systems, where various approaches have explored the application of neural networks in place of traditional designs. Neural networks flexibly allow for data/simulation-driven optimization, but are often employed as black boxes det…
Unified policy controls diverse agents through modular neural networks.
problem Learning control policies for various agent morphologies.
method Shared Modular Policies (SMP) with decentralized control and message passing.
result A single modular policy controls multiple agent morphologies.
Many prediction problems, such as those that arise in the context of robotics, have a simplifying underlying structure that, if known, could accelerate learning. In this paper, we present a strategy for learning a set of neural network modules that can be combined in different ways. We train different modular structure…
Training a Neural Network (NN) with lots of parameters or intricate architectures creates undesired phenomena that complicate the optimization process. To address this issue we propose a first modular approach to NN design, wherein the NN is decomposed into a control module and several functional modules, implementing …
This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph by computing "messages" based only on the representation of the source of each edge. In GNN-FiLM, the representation of the target node of an…
Bayesian Attention Modulesstat.ML
Bayesian attention modules improve model interpretability and performance.
problem Deterministic attention modules limit model interpretability and optimization.
method Proposes a scalable stochastic attention module using simplex-constrained distributions and Bayesian learning.
result Consistent improvements over baselines in various attention-based models.
Paper proposes a new pipeline for few-shot classification using forget-update module and channel vector sequence.
problem Few-shot classification with limited support samples.
method Channel vector sequence construction module and forget-update module.
result Pipeline achieves state-of-the-art results on various datasets.