Complex-valued neural networks are not a new concept, however, the use of real-valued models has often been favoured over complex-valued models due to difficulties in training and performance. When comparing real-valued versus complex-valued neural networks, existing literature often ignores the number of parameters, r…
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 “Real-Valued Neural Networks”
CVNN outperforms RVNN on non-circular data.
problem Classifying complex-valued data with statistical dependence.
method Comparison of CVNN and RVNN on non-circular data.
result CVNN outperforms RVNN in accuracy and generalization.
Recently, the connectionist temporal classification (CTC) model coupled with recurrent (RNN) or convolutional neural networks (CNN), made it easier to train speech recognition systems in an end-to-end fashion. However in real-valued models, time frame components such as mel-filter-bank energies and the cepstral coeffic…
Learning to predict solutions to real-valued combinatorial graph problems promises efficient approximations. As demonstrated based on the NP-hard edge clique cover number, recurrent neural networks (RNNs) are particularly suited for this task and can even outperform state-of-the-art heuristics. However, the theoretical…
Develops a binarized GNN for more efficient graph embeddings.
problem Real-valued GNN parameters limit efficiency and scalability.
method Integrates binarization into GNN-based graph embedding approaches.
result Binarized graph neural network (BGN) achieves state-of-the-art performance with significant efficiency gains.
Deep learning has become an area of interest in most scientific areas, including physical sciences. Modern networks apply real-valued transformations on the data. Particularly, convolutions in convolutional neural networks discard phase information entirely. Many deterministic signals, such as seismic data or electrica…
Optimization of Binarized Neural Networks (BNNs) currently relies on real-valued latent weights to accumulate small update steps. In this paper, we argue that these latent weights cannot be treated analogously to weights in real-valued networks. Instead their main role is to provide inertia during training. We interpre…
In recent years, hyper-complex deep networks (such as complex-valued and quaternion-valued neural networks) have received a renewed interest in the literature. They find applications in multiple fields, ranging from image reconstruction to 3D audio processing. Similar to their real-valued counterparts, quaternion neura…
We present a novel optimization strategy for training neural networks which we call "BitNet". The parameters of neural networks are usually unconstrained and have a dynamic range dispersed over all real values. Our key idea is to limit the expressive power of the network by dynamically controlling the range and set of …
We give a polynomial-time algorithm for learning neural networks with one layer of sigmoids feeding into any Lipschitz, monotone activation function (e.g., sigmoid or ReLU). We make no assumptions on the structure of the network, and the algorithm succeeds with respect to {\em any} distribution on the unit ball in …
Neural network architectures are at the core of powerful automatic speech recognition systems (ASR). However, while recent researches focus on novel model architectures, the acoustic input features remain almost unchanged. Traditional ASR systems rely on multidimensional acoustic features such as the Mel filter bank en…
This paper presents the recurrent estimation of distributions (RED) for modeling real-valued data in a semiparametric fashion. RED models make two novel uses of recurrent neural networks (RNNs) for density estimation of general real-valued data. First, RNNs are used to transform input covariates into a latent space to …
We introduce RNADE, a new model for joint density estimation of real-valued vectors. Our model calculates the density of a datapoint as the product of one-dimensional conditionals modeled using mixture density networks with shared parameters. RNADE learns a distributed representation of the data, while having a tractab…
Despite the superior performance of deep learning in many applications, challenges remain in the area of regression on function spaces. In particular, neural networks are unable to encode function inputs compactly as each node encodes just a real value. We propose a novel idea to address this shortcoming: to encode an …
Stochasticity and limited precision of synaptic weights in neural network models are key aspects of both biological and hardware modeling of learning processes. Here we show that a neural network model with stochastic binary weights naturally gives prominence to exponentially rare dense regions of solutions with a numb…
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.
New method uses neural nets in Hilbert space for option pricing on flow forwards.
problem Pricing options on flow forwards with neural networks in Hilbert space.
method Optimization problem in Hilbert space solved by a novel feedforward neural network architecture.
result Excellent numerical efficiency and superior performance over classical methods.
The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Modelscs.LG
This study examines how discretization improves neural forecasting models.
problem Improving predictive performance of neural forecasting models.
method Empirical investigation of data binning techniques on various neural forecasting architectures.
result Data binning almost always improves forecasting accuracy, but the type of binning is less important.
Significant success has been reported recently using deep neural networks for classification. Such large networks can be computationally intensive, even after training is over. Implementing these trained networks in hardware chips with a limited precision of synaptic weights may improve their speed and energy efficienc…
StrNN uses neural network structures to learn conditional independencies.
problem Learning conditional independencies in neural networks.
method Designing masks for neural networks based on binary matrix factorization.
result StrNN improves density estimation and causal inference.
Quaternion neural networks improve distant speech recognition.
problem Challenges in distant speech recognition due to noise and reverberation.
method Quaternion neural networks process multi-channel audio signals as quaternion entities, capturing internal and external dependencies.
result QLSTM outperforms real-valued LSTM on multi-channel distant speech recognition tasks.
NEMO framework quantizes DNNs for efficient deployment.
problem Efficient deployment of quantized DNNs.
method Formal framework for quantizing DNN layers, focusing on IntegerDeployable representation.
result Quantized DNNs can be deployed using only integers.
Survey of complex-valued neural networks for improved performance.
problem Lack of complex-valued neural networks in machine learning frameworks.
method Literature review of CVNNs.
result Advantages of CVNNs over real-valued neural networks.
This paper shows neural networks can solve complex graph problems efficiently.
problem Solving exact maximum flow computation and minimum spanning tree problems.
method Introduces Max-Affine Arithmetic Programs and shows equivalence to neural networks.
result Two combinatorial optimization problems can be solved with polynomial-size neural networks.
Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognitioneess.AS
Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition tasks, due to their efficient representation of long and short term dependencies …
Convolutional neural networks (CNN) have recently achieved state-of-the-art results in various applications. In the case of image recognition, an ideal model has to learn independently of the training data, both local dependencies between the three components (R,G,B) of a pixel, and the global relations describing edge…
Survival MDN uses invertible functions to speed up survival analysis models.
problem Training neural ODEs for survival analysis is computationally expensive.
method Survival MDN applies an invertible positive function to MDN outputs.
result Survival MDN outperforms or matches other models on concordance, Brier score, and log-likelihood.
Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience. Our main finding is that standard overparameterized deep neural networks trained using standard optimization methods implement such a mechanism for real-valued…
General lower bounds on neural network approximation in L^p norm.
problem Fundamental limits of neural network expressivity.
method General lower bound proof on approximation in L^p norm, applied to feed-forward neural networks.
result Neural networks can't approximate certain functions as well as previously thought.
Generalizes neural network approximation to infinite-dimensional manifolds and derivatives.
problem Approximating differentiable maps on infinite-dimensional manifolds.
method Proves a weighted Nachbin theorem to establish universal approximation for differentiable maps, including derivatives.
result Linear functions of the signature can approximate path space functionals including their derivatives.
Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or images recognition, involve multi-dimensional input features that are characteriz…
We present a new, unifying approach following some recent developments on the complexity of neural networks with piecewise linear activations. We treat neural network layers with piecewise linear activations as tropical polynomials, which generalize polynomials in the so-called or tropical algebra, with pos…
New algorithm reduces sample complexity for online reinforcement learning.
problem Reducing sample complexity for online reinforcement learning in nonlinear systems.
method Generalized algorithm for various dynamical systems, including neural networks.
result Achieves policy regret of O(Nε^2 + d_u ln(m(ε))/ε^2) in general settings.
Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features. We study the possibility of preventing such adversarial inference, yet without too much accuracy degradation. We propose a generic method to revise the neural network to boost the challe…
Proves SQ lower bounds for learning two-hidden-layer neural networks.
problem Learning two-hidden-layer ReLU networks with Gaussian inputs.
method Refined lifting procedure to reduce Boolean PAC learning to Gaussian.
result Superpolynomial SQ lower bounds for Gaussian inputs.
A dynamic Boltzmann machine (DyBM) has been proposed as a model of a spiking neural network, and its learning rule of maximizing the log-likelihood of given time-series has been shown to exhibit key properties of spike-timing dependent plasticity (STDP), which had been postulated and experimentally confirmed in the fie…
DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and Regularizationstat.ML
A new method prunes neural networks efficiently without losing effectiveness.
problem Efficient pruning of neural networks without sacrificing performance.
method Deterministic approximation of binary gates and regularization.
result Pruning neural networks significantly without loss in effectiveness.
This research evaluates the performance of an Artificial Neural Network based prediction system that was employed on the Shanghai Stock Exchange for the period 21-Sep-2016 to 11-Oct-2016. It is a follow-up to a previous paper in which the prices were predicted and published before September 21. Stock market price predi…
New neural networks model for spatio-temporal data.
problem Building a mapping from spatially encoded time series covariates to real-valued response data.
method Proposed two novel extensions of Functional Neural Network (FNN) for spatio-temporal regression.
result Demonstrated effectiveness in handling varying spatial correlations through comprehensive simulation studies.
Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max operator. We show that the gradient of this operator defines a mapping from real val…
This study uncovers how neural architectures and weights interact in classification tasks.
problem Understanding the role of neural architecture and weights in classification performance.
method Developed a novel method to find optimal task-specific architectures as binary networks with {0, 1}-valued weights, using approximate gradient descent.
result Well-trained architectures may not require fine-tuning of weights, highlighting the importance of structure over weights.
New Gaussian priors for neural networks improve scalability and Bayesian inference stability.
problem Scalability and stability issues in Bayesian neural network inference.
method Introduces a new Gaussian neural network prior with decreasing variance in network width, enabling stable MCMC sampling.
result The new prior enables stable MCMC sampling for Bayesian neural network inference, improving scalability and stability.
Generative Adversarial Networks (GANs) have shown remarkable success as a framework for training models to produce realistic-looking data. In this work, we propose a Recurrent GAN (RGAN) and Recurrent Conditional GAN (RCGAN) to produce realistic real-valued multi-dimensional time series, with an emphasis on their appli…
New bounds show complex neural networks need many queries to learn.
problem Learning non-polynomial activation functions with Gaussian marginals.
method Gradient boosting procedure to amplify lower bounds on SQ dimension of neural networks.
result Statistical-query lower bounds for ReLU regression with queries.
AttViz offers online visualizations of neural language model attention mechanisms.
problem Limited interpretability of neural language models.
method Online toolkit for exploring self-attention mechanisms.
result Visualizations help understand model decision-making.
In this article we consider macrocanonical models for texture synthesis. In these models samples are generated given an input texture image and a set of features which should be matched in expectation. It is known that if the images are quantized, macrocanonical models are given by Gibbs measures, using the maximum ent…
C-SURE improves complex-valued deep learning models by shrinking estimates, outperforming MLE and SurReal.
problem Improving accuracy and robustness of complex-valued deep learning models.
method Proposes a Stein's unbiased risk estimate (SURE) for complex-valued data and integrates it into a prototype CNN classifier.
result C-SURE outperforms SurReal and MLE in accuracy and robustness on complex-valued datasets.
AlgebraNetscs.LG
AlgebraNets use alternative algebras for neural networks, improving performance on image and language tasks.
problem Improving neural network performance on large-scale image and language tasks.
method Considered alternative algebras (C, H, M2(R), M2(C), M3(R), M4(R)) for activations and weights, and studied their performance on ImageNet and enwiki8 datasets.
result Alternative algebras deliver better parameter and computational efficiency compared with real numbers, especially in sparse and auto-regressive inference scenarios.