In this paper, a simple, general method of adding auxiliary stochastic neurons to a multi-layer perceptron is proposed. It is shown that the proposed method is a generalization of recently successful methods of dropout (Hinton et al., 2012), explicit noise injection (Vincent et al., 2010; Bishop, 1995) and semantic has…
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 “Multi-Layer Perceptron”
New method initializes sigmoidal MLPs for interpretable shapes.
problem Creating interpretable decision boundaries in neural networks.
method Introducing a geometry-aware initialization for sigmoidal multi-layer perceptrons (MLPs) using tropical geometry.
result Sigmoidal MLPs can have decision boundaries aligned with prescribed shapes at initialization.
Noise causes learning plateaus in neural networks.
problem Plateau phenomena in online learning due to vanishing gradients.
method Analysis of stochastic gradient descent in multi-layer perceptrons.
result Noise induces synchronisation leading to strong plateaus.
We consider the problem of reconstructing a signal from multi-layered (possibly) non-linear measurements. Using non-rigorous but standard methods from statistical physics we present the Multi-Layer Approximate Message Passing (ML-AMP) algorithm for computing marginal probabilities of the corresponding estimation proble…
New view: Deep GCNs learn to anti-oversmooth during training.
problem Performance drop in deep GCNs due to oversmoothing.
method Interpreted GCN as MLP + graph regularization, analyzed training process.
result Deep GCNs learn to anti-oversmooth during training, not over-smooth.
Deep learning outperforms traditional methods in estimating OU process parameters.
problem Parameter estimation of the Ornstein-Uhlenbeck process is challenging.
method Used a multi-layer perceptron to estimate OU process parameters compared to traditional methods like Kalman filter and maximum likelihood estimation.
result Deep learning method outperforms traditional methods in parameter estimation of the OU process.
This study compares GNNs and GA-MLPs, finding GA-MLPs can distinguish graphs but not count walks.
problem Comparing expressive power and graph isomorphism testing capabilities of GNNs and GA-MLPs.
method GA-MLPs augment node features with multi-hop operators and apply MLPs node-wise; GNNs are compared as a baseline.
result GA-MLPs can distinguish almost all non-isomorphic graphs but cannot count attributed walks, unlike GNNs.
Proposes a balanced multi-component and multi-layer neural network for efficient function approximation.
problem Accurately and efficiently approximating complex functions with high degrees of freedom and computational cost.
method Inspired by a multi-component approach, MMNN combines single-layer networks with a multi-layer decomposition strategy.
result Significant reduction in training parameters, more efficient training process, and improved accuracy compared to FCNNs or MLPs.
Efficiently predicts long-time dynamics of quantum spin models using MLP regression.
problem Challenges in calculating long-time expectation values for quantum spin models.
method Utilized a multi-layer perceptron (MLP) model for regression on matrix product states (MPS) expectation values.
result Significantly reduced computational cost for generating long-time dynamics while maintaining high accuracy.
Hybrid model improves wind speed prediction accuracy using MLP and WOA.
problem Improving wind speed prediction accuracy for renewable energy control.
method Combining MLP with Whale Optimization Algorithm (WOA) for data preprocessing and model optimization.
result The hybrid MLP-WOA model outperformed standalone MLP model in wind speed prediction accuracy.
Proposes a new model for high-dimensional data analysis with unknown link function.
problem Estimating link function, component functions, and variable interactions in high-dimensional data.
method Generalized Sparse Additive Model with Unknown Link Function (GSAMUL) using B-spline basis and MLP network for link estimation, with -norm regularizer for variable selection.
result Can realize both variable selection and hidden interaction.
Model predicts anti-cancer drug responses using gene and molecular data.
problem Expensive and time-consuming cancer drug discovery and tailoring.
method Uses variational autoencoders and multi-layer perceptrons to encode gene expression and drug data.
result High average of 0.83 and 0.845 in predicting drug responses for breast and pan-cancer cell lines, respectively.
The paper improves ESG taxonomy and classifies sentences as sustainable or unsustainable.
problem Improving ESG taxonomy and classifying sentences based on ESG factors.
method For ESG taxonomy, used Sentence-BERT models. For sentence classification, combined RoBERTa with a multi-layer perceptron.
result Significant performance improvement and high accuracy in classifying sentences.
A new model improves the performance of knowledge distillation in GNNs.
problem Inconsistent performance of existing knowledge distillation techniques in GNNs.
method Proposes a new model, Routing-by-Memory (RbM), a form of Mixture-of-Experts (MoE), to address performance concerns.
result Demonstrates experimentally that RbM achieves considerably more consistent performance across multiple datasets.
Model predicts customer churn in financial institutions using neural networks.
problem Manual feature engineering in customer churn prediction.
method Developed a Multi-layer Perceptron model using Artificial Neural Network architecture.
result Artificial Neural Network model achieved comparable performance to Neuro Solution Infinity software.
Enhanced neural networks detect thin boundaries between different types of anomalies.
problem Detecting thin boundaries between different types of anomalies in outlier detection.
method Defined new types of anomalies, enhanced Multi-Layer Perceptron Neural Network with Genetic Algorithm.
result Reduced error in anomaly detection compared to baseline methods.
Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversarial Networks (GANs) can learn data distributions without needing a parametric assumption on the output density. We show on a speech source se…
Image recognition using Deep Learning has been evolved for decades though advances in the field through different settings is still a challenge. In this paper, we present our findings in searching for better image classifiers in offline and online environments. We resort to Convolutional Neural Network and its variatio…
Deep-n-Cheap automates deep learning model search for low complexity.
problem Finding efficient deep learning models for various datasets.
method Automated search framework for architecture and hyperparameters, including search transfer.
result Models offer comparable performance to state-of-the-art but are faster to train.
This study approximates neural network features for modeling relations and attention mechanisms.
problem Approximating neural network features for modeling relations and attention mechanisms.
method Analyzes inner products of multi-layer perceptrons for universal approximation of symmetric and asymmetric relation functions.
result Universal approximation of relation functions and attention mechanisms using inner products of neural networks.
Dropout is a very effective method in preventing overfitting and has become the go-to regularizer for multi-layer neural networks in recent years. Hierarchical mixture of experts is a hierarchically gated model that defines a soft decision tree where leaves correspond to experts and decision nodes correspond to gating …
This review tackles long horizon forecasting in time series analysis using deep learning.
problem Long horizon forecasting in time series analysis.
method Incorporates deep learning techniques such as trend, seasonality, Fourier and wavelet transforms, and various model architectures.
result LHF is an error propagation problem, with models like xLSTM and Triformer showing better performance.
New priors for deep neural networks converge to Gaussian processes.
problem Improving the performance and stability of deep neural networks.
method Extending prior distributions to include non-zero means and partially exchangeable priors, leading to a new Gaussian process model.
result The new Gaussian process model avoids pathologies and improves performance on regression problems.
Transformers can scale both context and task, but MLPs can only scale task.
problem Understanding and scaling In-Context Learning in transformers.
method Simplified transformer architecture, feature map, and MLP combination.
result Simplified transformer can perform ICL and context-scaling but not task-scaling.
AMEIR automates recommender system design using NAS.
problem Manual feature and architecture engineering in recommender systems.
method Three-stage search space and tailored three-step pipeline.
result AMEIR outperforms manual and complex NAS methods.
Meta-learning consists in learning learning algorithms. We use a Long Short Term Memory (LSTM) based network to learn to compute on-line updates of the parameters of another neural network. These parameters are stored in the cell state of the LSTM. Our framework allows to compare learned algorithms to hand-made algorit…
In this research, Artificial Neural Networks (ANNs) have been used as a powerful tool to solve the inverse kinematic equations of a parallel robot. For this purpose, we have developed the kinematic equations of a Tricept parallel kinematic mechanism with two rotational and one translational degrees of freedom (DoF). Us…
Binary encoding enables neural networks to extrapolate periodic functions.
problem Extrapolating periodic functions without prior knowledge of their form.
method Normalized Base-2 Encoding (NB2E) for continuous numerical values.
result MLPs using NB2E can successfully extrapolate diverse periodic signals.
Hypernetworks are neural networks that generate weights for another neural network. We formulate the hypernetwork training objective as a compromise between accuracy and diversity, where the diversity takes into account trivial symmetry transformations of the target network. We explain how this simple formulation gener…
We propose Very Simple Classifier (VSC) a novel method designed to incorporate the concepts of subsampling and locality in the definition of features to be used as the input of a perceptron. The rationale is that locality theoretically guarantees a bound on the generalization error. Each feature in VSC is a max-margin …
pystacked combines machine learning models for improved predictions.
problem Improving machine learning model performance through stacking.
method Stacked generalization using Python's scikit-learn with various base learners.
result Enhanced predictive models through combining multiple machine learning algorithms.
Neural networks allow Q-learning reinforcement learning agents such as deep Q-networks (DQN) to approximate complex mappings from state spaces to value functions. However, this also brings drawbacks when compared to other function approximators such as tile coding or their generalisations, radial basis functions (RBF) …
Bayesian optimization has recently emerged as a popular and efficient tool for global optimization and hyperparameter tuning. Currently, the established Bayesian optimization practice requires a user-defined bounding box which is assumed to contain the optimizer. However, when little is known about the probed objective…
Statistical physics explains deep learning's feature learning capacity.
problem Understanding neural networks' ability to learn complex features.
method Study of a multi-layer perceptron in the interpolation regime.
result Optimal learning requires specialization across layers and neurons.
A scalable parallel BO method for asynchronous settings.
problem Expensive-to-evaluate problems in machine learning.
method Simple and scalable Bayesian optimization method for asynchronous parallel settings.
result Demonstrated promising performance on benchmark functions and hyperparameter optimization.
Autonomous construction of deep neural network (DNNs) is desired for data streams because it potentially offers two advantages: proper model's capacity and quick reaction to drift and shift. While the self-organizing mechanism of DNNs remains an open issue, this task is even more challenging to be developed for standar…
Proof of learning rate transfer in MLPs with P parameterization.
problem Understanding and optimizing learning rates in neural networks with different parameterizations.
method Theoretical analysis and empirical validation of learning rate transfer in MLPs with P, SP, and NTP parameterizations.
result The optimal learning rate converges to a non-zero constant as width goes to infinity under P, explaining learning rate transfer.
Paper tackles many-class few-shot learning with class hierarchy, improving accuracy.
problem Many-class few-shot learning problem in practical applications.
method Leverages class hierarchy to train a coarse-to-fine classifier using memory-augmented hierarchical-classification network (MahiNet).
result MahiNet outperforms state-of-the-art models on MCFS problems in both supervised and meta-learning settings.
This study compares mtl architectures for renewable power generation forecasting.
problem Forecasting expected power generation for renewable power plants.
method Comparative study of mtl architectures including Hard parameter sharing, cross-stitch network, sluice network, and task embedding.
result Emerging Relation Network (ERN) and task embedding provide significant improvements in forecasting.
DMIDAS improves long-term forecasting accuracy in healthcare and electricity data.
problem Challenging long-term forecasting accuracy and computational complexity.
method Smoothness regularization and mixed data sampling techniques integrated into NBEATS architecture.
result Improves prediction accuracy by 5% on long forecasting horizons (1000 timestamps) compared to state-of-the-art models.
FNNs detect EEG signals without position dependence.
problem Detecting EEG signals without position dependence.
method Shift invariant functional neural networks (FNNs) using FDA methods.
result FNNs outperform FDA benchmarks in EEG classification.
Improved graph generation model for small organic molecules.
problem Graph generation models struggle with matching training distributions and require expensive graph matching.
method Introduced a message passing neural network into the GVAE's encoder and decoder.
result Demonstrated improved graph generation for small organic molecules.
In this paper, we present an experimental study for the classification of perceived human stress using non-invasive physiological signals. These include electroencephalography (EEG), galvanic skin response (GSR), and photoplethysmography (PPG). We conducted experiments consisting of steps including data acquisition, fe…
We have applied a little-known data transformation to subsets of the Surveillance, Epidemiology, and End Results (SEER) publically available data of the National Cancer Institute (NCI) to make it suitable input to standard machine learning classifiers. This transformation properly treats the right-censored data in the …
This study presents an extension of the Gaussian process regression model for multiple-input multiple-output forecasting. This approach allows modelling the cross-dependencies between a given set of input variables and generating a vectorial prediction. Making use of the existing correlations in international tourism d…
This paper explores the capability of deep neural networks to capture key characteristics of vehicle dynamics, and their ability to perform coupled longitudinal and lateral control of a vehicle. To this extent, two different artificial neural networks are trained to compute vehicle controls corresponding to a reference…
Single neuron with ADA learns XOR and outperforms other functions.
problem Classifying linearly non-separable data.
method Proposed a new artificial neuron with apical dendrite activation.
result ADA function achieves 100% accuracy on XOR and superior performance on benchmark datasets.
Smooth KANs improve model reliability in computational biomedicine.
problem Limited convergence of KANs in representing generic smooth functions.
method Introducing smooth, structurally informed KANs that can approximate MLPs in specific function classes.
result Smooth KANs can achieve equivalence to MLPs in specific function classes, enhancing model reliability and performance.