New method learns both module structure and sequencing in neural networks.
problem Learning only the parameters and order of execution of neural modules.
method Expands the approach to learn the internal structure of modules, including the ordering and combination of arithmetic operators.
result Performance comparable to hand-designed modules achieved without extra supervisory signals.
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.
Some neural network modules are more critical to performance than others.
problem Understanding why some neural network architectures generalize better than others.
method Introduced module criticality, a measure based on the shape of loss valleys.
result Module criticality explains superior generalization performance of some architectures.
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.
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.
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…
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.
GNN-FiLM uses feature-wise linear modulation to improve graph neural networks.
problem Improving graph neural networks for better performance.
method Feature-wise linear modulation applied to target node representations in GNNs.
result GNN-FiLM outperforms baseline methods on a regression task for molecular graphs.
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…
A new method learns representations without end-to-end backpropagation.
problem Learning representations without labeled data and end-to-end backpropagation.
method Gradient-isolated modules trained using InfoNCE bound.
result Top module's representations yield competitive results on downstream tasks.
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.
Dynamic information balancing reduces catastrophic forgetting in modular neural networks.
problem Catastrophic forgetting in neural networks when learning multiple tasks.
method Dynamic Information Balancing (DIB) using reinforcement learning to adaptively route inputs based on module information load.
result DIB combined with EWC regularization outperforms models with similar capacity and EWC regularization.
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.
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 …
New tensor network decompositions improve CNN performance.
problem Limited exploration of tensor network decompositions for CNNs.
method Characterized a new class of CNN modules and experimentally compared various decompositions.
result Some nonlinear decompositions outperform existing ones in terms of accuracy and efficiency.
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.
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.
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.
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…
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.
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.
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.
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.
Neural network detects spectrum signals under uncertain parameters.
problem Spectrum sensing under uncertain primary user signal parameters.
method Trained neural network to detect modulated signals robustly.
result Neural network gains robustness under carrier frequency, phase, and symbol time offsets.
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.
LGM-Net learns transferable prior knowledge for few-shot learning.
problem Few-shot classification with limited training data.
method Meta-learning approach with TargetNet and MetaNet modules.
result LGM-Net achieves competitive performance on unseen tasks.
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.
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.
PSTN improves traffic condition forecasting with deep neural networks.
problem Challenges in accurately forecasting traffic conditions due to complex spatiotemporal correlations.
method Proposes PSTN with three modules: graph convolutional network, temporal convolutional network, and gated recurrent unit framework.
result Significantly outperforms state-of-the-art benchmarks in short-term traffic conditions forecasting.
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…
New approach uses prior knowledge to improve neural network representations.
problem Difficulty in learning robust internal representations without a large training set.
method Incorporates prior information into a pre-trained reasoning module.
result Improves representation learning in diverse self-supervised learning settings.
PyDEns framework uses neural nets to solve PDEs.
problem Lack of flexible framework for solving PDEs with neural networks.
method PyDEns-module coupled with BatchFlow, allowing to solve PDEs, search for neural network architectures, and control model training.
result Ready-to-use and open-source numerical solver of PDEs based on neural networks.
TFiLM expands convolutional models' receptive field with minimal overhead.
problem Capturing long-range dependencies in sequential data.
method A novel architectural component using a recurrent neural network to modulate convolutional model activations.
result TFiLM significantly improves learning speed and accuracy on various tasks.
An artificial agent for financial risk and returns' prediction is built with a modular cognitive system comprised of interconnected recurrent neural networks, such that the agent learns to predict the financial returns, and learns to predict the squared deviation around these predicted returns. These two expectations a…
Express Wavenet reduces neural network parameters to 1% of standard networks.
problem Optical neural networks with high parameter count.
method Wavelet modulation, random shift wavelets, expressway structure.
result Express Wavenet achieves high accuracy with significantly fewer parameters.
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…
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.
Combines Hebbian and DQN for better POMDP problem solving.
problem Difficult POMDP problems with TD errors.
method Modulated Hebbian plus Q network architecture (MOHQA) integrating Hebbian and DQN.
result Improved DQN performance and outperformed other algorithms on some POMDPs.
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…
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.
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.
This paper improves GNNs' generalization by adding a Low-Rank Global Attention module.
problem Improving the generalization power of Graph Neural Networks (GNNs).
method Incorporating a Low-Rank Global Attention (LRGA) module into GNNs.
result Augmenting GNNs with LRGA aligns them with a powerful graph isomorphism test, 2-Folklore Weisfeiler-Lehman (2-FWL).
In this paper, a neural network-aided bit-interleaved coded modulation (NN-BICM) receiver is designed to mitigate the nonlinear clipping distortion in the LDPC coded direct currentbiased optical orthogonal frequency division multiplexing (DCOOFDM) systems. Taking the cross-entropy as loss function, a feed forward netwo…
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 …
The artificial neural network shows powerful ability of inference, but it is still criticized for lack of interpretability and prerequisite needs of big dataset. This paper proposes the Rule-embedded Neural Network (ReNN) to overcome the shortages. ReNN first makes local-based inferences to detect local patterns, and t…
Enhances GNNs for causal relationship learning.
problem Lack of robust causal modeling in GNNs.
method Synthesized dataset with known causal relationships, lightweight GNN module.
result Empirically validated GNN module improves causal learning.
Random forest and deep neural network are two schools of effective classification methods in machine learning. While the random forest is robust irrespective of the data domain, the deep neural network has advantages in handling high dimensional data. In view that a differentiable neural decision forest can be added to…