We present a comprehensive study of multilayer neural networks with binary activation, relying on the PAC-Bayesian theory. Our contributions are twofold: (i) we develop an end-to-end framework to train a binary activated deep neural network, (ii) we provide nonvacuous PAC-Bayesian generalization bounds for binary activ…
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 “binary neural activations”
BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activationscs.LG
BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.
problem Gradient mismatch in BNNs due to binarizing activations.
method Using gradient of smoothed loss function to estimate gradient mismatch, proposing BinaryDuo scheme with coupled ternary activations.
result BinaryDuo outperforms state-of-the-art BNNs on various benchmarks.
Paper proposes HTAF for stable training of binary neural networks.
problem Challenges in training binary neural networks with gradient-based optimization.
method HTAF is a smooth approximation to the Heaviside function that enables stable training.
result HTAF enables stable training of various binary neural networks with gradient-based optimization.
We introduce a novel scheme to train binary convolutional neural networks (CNNs) -- CNNs with weights and activations constrained to {-1,+1} at run-time. It has been known that using binary weights and activations drastically reduce memory size and accesses, and can replace arithmetic operations with more efficient bit…
Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networksstat.ML
Reintroduces straight-through estimators for binary neural networks.
problem Training neural networks with binary weights and activations is challenging due to gradient issues and discrete weight optimization.
method Derives ST methods as estimators in the SBN model, analyzes properties and estimation accuracy, explains latent weights and mirror descent method.
result Reintroduces ST methods as sound approximations and provides clearer application and improvements.
This paper analyzes the training dynamics of binary neural networks using information bottleneck.
problem Training binary neural networks is challenging due to discontinuity in activation functions.
method The approach uses the Information Bottleneck principle to analyze BNN training dynamics.
result Training dynamics of BNNs are different from DNNs, with both phases occurring simultaneously.
New algorithm trains binary-activation, multi-level RNNs for noise-resilient, ADC-/DAC-free PIM inference.
problem Training noise-resilient, ADC-/DAC-free neural networks.
method Binary activations and multi-level weights for eNVM-based processing-in-memory circuits.
result Higher accuracy and noise resilience for recurrent networks compared to existing methods.
Binary autoencoder with sparse hidden layer preserves information and zero reconstruction error.
problem Preserving information and zero reconstruction error in binary neural networks.
method Binary autoencoder with random binary weights, sparse hidden layer, and varying neuron thresholds.
result Zero reconstruction error for any input with a large hidden layer and varying neuron thresholds.
Dual neural network architecture improves accuracy and interpretability.
problem Improving neural network interpretability and accuracy.
method Stacked recurrent and feedforward layers, binary activation function.
result Binary activation leads to simpler, more interpretable models with higher accuracy.
MeliusNet improves binary neural networks to match MobileNet-v1 accuracy.
problem Achieving high accuracy with binary neural networks on mobile devices.
method Alternating DenseBlocks and ImprovementBlocks to increase feature capacity and quality.
result MeliusNet matches MobileNet-v1 accuracy on ImageNet, improving binary network performance.
Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both binary weights and activations, called BLRNet. By embracing stochasticity during tr…
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.
Model detects patterns in noisy binary data, explaining neuron activity in terms of cell assemblies.
problem Detecting structure in noisy or approximate repeats of patterns in sparse binary data.
method Probabilistic binary latent variable model based on Noisy-OR model, inferring sparse activity in latent variables.
result Model successfully extracts and explains latent structure in spiking neural data.
New method for estimating gradients in stochastic binary networks.
problem Challenges in training neural networks with binary activations and weights.
method Combines sampling and analytic approximation steps to estimate gradients accurately.
result Significantly reduced variance at the cost of small bias, leading to practical tradeoffs.
Generalizes NTK for surrogate gradient learning in neural networks.
problem Lack of theoretical foundation for surrogate gradient learning.
method Generalizes neural tangent kernel (NTK) for surrogate gradient learning (SGL).
result Surrogate gradient NTK provides a good characterization of SGL.
Quantized neural networks can represent all fixed-point functions under certain conditions.
problem Expressive power of quantized neural networks under fixed-point arithmetic.
method Analyzing necessary and sufficient conditions for quantized networks to represent all fixed-point functions.
result Various popular activation functions satisfy the sufficient condition for representing all fixed-point functions.
Deep learning has become a powerful and popular tool for a variety of machine learning tasks. However, it is challenging to understand the mechanism of deep learning from a theoretical perspective. In this work, we propose a random active path model to study collective properties of deep neural networks with binary syn…
Efficient Bitwidth Search optimizes neural network quantization for better performance.
problem Finding optimal bitwidth for weights and activations of each layer efficiently.
method EBS algorithm reusing meta weights and binary decomposition for efficient mixed precision convolution.
result Mixed precision QNN outperforms uniform bitwidth and other techniques on CIFAR10 and ImageNet.
Neural networks with low-precision weights and activations offer compelling efficiency advantages over their full-precision equivalents. The two most frequently discussed benefits of quantization are reduced memory consumption, and a faster forward pass when implemented with efficient bitwise operations. We propose a t…
Neural plasticity is an important functionality of human brain, in which number of neurons and synapses can shrink or expand in response to stimuli throughout the span of life. We model this dynamic learning process as an -norm regularized binary optimization problem, in which each unit of a neural network (e.g., …
Study on double descent behavior in two-layer neural networks for binary classification.
problem Understanding the double descent phenomenon in model test error.
method Two-layer neural network with ReLU activation for binary classification. Quantified model size by sample-to-dimension ratio. Empirical risk minimization using Convex Gaussian Min Max Theorem.
result Observed and investigated the double descent behavior of model test error.
The paper examines topological features of ReLU networks and their relation to decision boundaries and training loss.
problem Understanding the topological structure of ReLU neural network activation patterns.
method Polytope decomposition of feature space, Fiedler partition of dual graph, homology computation of cellular decomposition.
result The Fiedler partition of the dual graph correlates with decision boundaries in binary classification tasks, and similar patterns in training loss and polyhedral cell-count emerge in regression tasks.
Variational mean-field theory for training restricted Boltzmann machines with binary synapsesstat.ML
Unified theory for training neural networks with binary synapses.
problem Discrete nature of synapses and complex interactions in neural networks.
method Variational mean-field theory decomposing learning into maximization and expectation steps.
result Unified framework for unsupervised learning in neural networks.
Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completionphysics.chem-ph
New method predicts activity coefficients for binary mixtures without using physical descriptors.
problem Predicting activity coefficients for unexplored binary mixtures.
method Probabilistic matrix factorization model.
result Method outperforms state-of-the-art models requiring less training effort.
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…
WrapNet optimizes inference for low-resolution neural networks by using 8-bit additions.
problem Reducing multiplication complexity in low-resolution neural networks.
method Adapting neural networks to use low-resolution (8-bit) additions in accumulators, with a cyclic activation layer and overflow penalty regularizer.
result Achieves comparable classification accuracy to 32-bit counterparts using low-resolution additions.
The training of stochastic neural network models with binary () weights and activations via continuous surrogate networks is investigated. We derive new surrogates using a novel derivation based on writing the stochastic neural network as a Markov chain. This derivation also encompasses existing variants of the s…
RBMs model binary interactions with hidden node activation effects.
problem Understanding how RBM hidden node activation affects binary variable distributions.
method Investigated RBM marginal distributions with different hidden node activation functions.
result Found exact expressions for RBM marginals as interacting binary variables.
Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines. Active ML aims to address this issue by designing learning algorithms that automatically and adaptively select the most informative examples for labeling so that human time is not wasted labeling irrelevant, redundant…
This research sets limits on how complex multi-class learning problems can be.
problem Understanding the complexity of multi-class classification problems.
method Established upper bounds on Natarajan dimensions for specific function classes.
result Upper bounds on Natarajan dimensions for multi-class decision trees, random forests, and neural networks.
In this paper, we propose majority voting neural networks for sparse signal recovery in binary compressed sensing. The majority voting neural network is composed of several independently trained feedforward neural networks employing the sigmoid function as an activation function. Our empirical study shows that a choice…
Binary neural networks (BNN) have been studied extensively since they run dramatically faster at lower memory and power consumption than floating-point networks, thanks to the efficiency of bit operations. However, contemporary BNNs whose weights and activations are both single bits suffer from severe accuracy degradat…
Continuous Dropoutcs.CV
Continuous dropout mimics brain neuron firing rates to prevent feature detector co-adaptation.
problem Preventing overfitting in deep neural networks.
method Extending binary dropout to continuous dropout, inspired by brain neuron firing rates.
result Continuous dropout improves test performance by preventing feature detector co-adaptation.
This paper improves SNN training by using multiple sample compartments.
problem Training SNNs with single-sample estimators leads to inaccurate log-likelihood estimates.
method Proposes a GEM-based online learning algorithm that uses multiple independent spiking signals.
result Significant improvements in log-likelihood, accuracy, and calibration with multiple compartments.
Convexifying Sparse Interpolation with Infinitely Wide Neural Networks: An Atomic Norm Approachcs.LG
This study uses neural networks to solve interpolation problems with sparse, infinitely wide layers.
problem Exact data interpolation using sparse, infinitely wide neural networks.
method Atomic norm framework to derive convex hulls and equivalent convex formulations.
result Simple characterizations of convex hulls for different constraints on network weights and biases.
Tropical division approximates polynomial division for neural networks.
problem Approximating polynomial division in max-plus semiring.
method Approximating Newton Polytope of dividend by divisor, then applying to neural networks.
result Minimizes a two-layer fully connected network for binary classification.
Erbium-doped fiber amplifier (EDFA) is an optical amplifier/repeater device used to boost the intensity of optical signals being carried through a fiber optic communication system. A highly accurate EDFA model is important because of its crucial role in optical network management and optimization. The input channels of…
We propose a new batch mode active learning algorithm designed for neural networks and large query batch sizes. The method, Discriminative Active Learning (DAL), poses active learning as a binary classification task, attempting to choose examples to label in such a way as to make the labeled set and the unlabeled pool …
There is a pressing need to build an architecture that could subsume these networks under a unified framework that achieves both higher performance and less overhead. To this end, two fundamental issues are yet to be addressed. The first one is how to implement the back propagation when neuronal activations are discret…
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.
Solution space and storage capacity of fully connected two-layer neural networks with generic activation functionscond-mat.dis-nn
Study on neural networks' storage capacity and solution space structure.
problem Understanding the storage capacity and solution space structure of neural networks.
method Replica method from statistical physics.
result Storage capacity per parameter remains finite even with infinite width and weights exhibit negative correlations.
We consider active maximum a posteriori (MAP) inference problem for Hidden Markov Models (HMM), where, given an initial MAP estimate of the hidden sequence, we select to label certain states in the sequence to improve the estimation accuracy of the remaining states. We develop an analytical approach to this problem for…
Paper tackles binary feedbacks in contextual search learning.
problem Learning underlying mean value function in context with binary feedbacks.
method Tri-section search combined with margin-based active learning.
result Algorithm achieves queries for -estimation accuracy.
The paper tackles uniform sampling from neural networks efficiently.
problem Uniform sampling from neural network labelings given a sample.
method Polynomial-time algorithm for general neural networks, random walk for single neuron.
result Uniform sampling with high probability for general neural networks, exact uniform sampling for single neuron.
A neural network with a single hidden layer can't represent certain multivariable functions.
problem Representing certain multivariable functions with a neural network having only one hidden layer.
method Developed a continuum version of a one-hidden-layer neural network with ReLU activation, and proved constraints on its parameters and second derivative.
result Existence of a smooth binary function that cannot be precisely represented by any such neural network.
The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networkscs.LG
SGD converges to critical points of normalized margin in late-stage training for homogeneous neural networks.
problem Analyzing the implicit bias of SGD on homogeneous neural networks.
method Interpreting SGD dynamics as an Euler-like discretization of a conservative field flow associated with the normalized classification margin.
result Normalized SGD iterates converge to the set of critical points of the normalized margin at late-stage training.
The mesoscopic organization of complex systems, from financial markets to the brain, is an intermediate between the microscopic dynamics of individual units (stocks or neurons, in the mentioned cases), and the macroscopic dynamics of the system as a whole. The organization is determined by "communities" of units whose …
Quantization, a commonly used technique to reduce the memory footprint of a neural network for edge computing, entails reducing the precision of the floating-point representation used for the parameters of the network. The impact of such rounding-off errors on the overall performance of the neural network is estimated …