New method learns neural network activation functions from data.
problem Learning activation functions for neural networks.
method Model each neuron's activation function as a small neural network.
result Learned activation functions improve network performance.
This paper explores adaptive neural activation in RNNs for better learning.
problem Fixed neural activation functions limit the performance and adaptability of RNNs.
method Developed a novel parametric family of nonlinear activation functions inspired by biological neurons.
result Adaptive neural activation improves learning speed and performance in RNNs.
Deep learning models outperform classical methods in forecasting neural activity.
problem Improving forecasting of neural activity using deep learning models.
method Systematic evaluation of eight probabilistic deep learning models against classical statistical models and baseline methods.
result Several deep learning models consistently outperform classical approaches in forecasting neural activity.
Unified study of active learning for deep neural networks.
problem Improving performance of deep neural networks through active learning.
method Investigation of incremental and cumulative training modes, model configurations, query strategies, and pseudo-labels.
result Proposed more efficient querying procedures and insights into active learning behavior.
This paper provides an overview of activation functions in neural networks.
problem Confusion in activation function selection and properties in deep learning.
method Analytic review of popular activation functions.
result Clarification of activation function properties and selection.
Neural networks learn distance-based representations, not just intensity.
problem Understanding how neural networks interpret and learn from internal activations.
method Manipulated ReLU and Absolute Value activations to observe sensitivity to distance and intensity perturbations.
result Neural networks are highly sensitive to small distance-based perturbations, challenging the intensity-based interpretation.
Paper provides label complexity guarantees for deep active learning.
problem Lack of rigorous label complexity guarantees for deep active learning.
method Studied deep active learning from nonparametric classification perspective.
result Proved near-optimal label complexity guarantees for deep active learning.
Abstract: Investigates the role of activation functions in neural networks and their physical basis.
problem Understanding the role of activation functions in neural networks and their physical basis.
method Formalizes the use of activation functions in neural inference by relating them to phase transitions in statistical physics.
result Reveals the physical justification for the performance of typical activation functions in neural networks.
Paper examines power consumption in neural networks using various activation functions.
problem Power consumption in machine learning models.
method Examines power consumption for different activation functions.
result Substantial differences in power consumption exist between activation functions.
We consider active learning of deep neural networks. Most active learning works in this context have focused on studying effective querying mechanisms and assumed that an appropriate network architecture is a priori known for the problem at hand. We challenge this assumption and propose a novel active strategy whereby …
Rational neural networks approximate functions more efficiently with less depth.
problem Choosing optimal nonlinear activation functions in neural networks.
method Rational activation functions with optimal bounds and efficiency proofs.
result Rational neural networks approximate smooth functions more efficiently than ReLU networks with exponentially smaller depth.
The paper analyzes the role of ReLU gates in deep learning networks.
problem Understanding the role of gates in deep learning networks.
method Developed neural path features (NPF) and neural path values (NPV) to characterize the active sub-networks during training.
result The neural path kernel associated with NPFs is a fundamental quantity that characterizes the information stored in the gates of a DNN.
Active learning method for neural population dynamics using optogenetics.
problem Efficiently selecting neurons to stimulate for identifying neural population dynamics.
method Developed active learning procedure for low-rank regression to determine informative photostimulation patterns.
result Demonstrated a two-fold reduction in data required for predictive power using low-rank linear dynamical systems model.
We develop a method to learn neural network activations with controlled Lipschitz constant.
problem Increase neural network capacity while controlling Lipschitz constant.
method Variational framework to learn activation functions with piecewise-linear constraints.
result Proves existence of solutions with continuous and piecewise-linear activations.
New method uses neural tangent kernel for efficient active learning.
problem Efficiently approximating deep learning's look-ahead selection criteria.
method Approximates retraining with neural tangent kernel for active learning.
result Approximation works asymptotically and enables sequential active learning.
INP accelerates stochastic simulations using deep Bayesian active learning.
problem Computational expense of stochastic simulations at fine-grained resolution.
method Interactive Neural Process (INP) framework combining spatiotemporal surrogate model and active learning acquisition function.
result STNP outperforms baselines in accelerating stochastic simulations and LIG achieves state-of-the-art for Bayesian active learning.
Neural networks struggle with periodic functions, a new activation fixes this.
problem Neural networks fail to learn simple periodic functions.
method Proposed a new activation function, x+sin2(x), to learn periodic functions. result The new activation function successfully learns and predicts periodic functions.
Polynomial time algorithm learns depth-2 neural networks with ReLU activations.
problem Learning depth-2 neural networks with non-zero bias terms and general ReLU activations.
method Robust tensor decomposition of Hermite expansions.
result Polynomial time and sample efficient learning of depth-2 networks with ReLU activations.
New method speeds up neural kernel computations for various activations.
problem Inefficient computation of neural kernels for general activations.
method Fast sketching method using truncated Hermite expansion.
result 106x speedup for approximate CNTK computation on CIFAR-10.
Deep neural networks with piecewise-polynomial activations can approximate smooth functions and their derivatives.
problem Approximating smooth functions and their derivatives with neural networks.
method Derives the depth, width, and sparsity required for approximation in Hölder norms.
result Deep neural networks with bounded weights can approximate Hölder smooth functions and their derivatives.
Evolutionary algorithms improve neural network performance by discovering better activation functions.
problem The choice of activation function affects neural network performance, but ReLU remains dominant.
method Defined a tree-based search space of candidate activation functions and used evolutionary algorithms (mutation, crossover, exhaustive search) to explore and discover better functions.
result Replacing ReLU with evolved activation functions statistically significantly increases network accuracy.
Visualizes deep neural networks for speech recognition using learned topographic filter maps.
problem Unintuitive internal structure of deep neural networks complicates activation visualization.
method Trains a convolutional speech recognition model with filters arranged in a 2D grid, highlighting similar filters.
result Topographic filter maps visualize artificial neuron activations more intuitively.
Mixtures of neural operators reduce active complexity in operator learning.
problem Reduction of active complexity in operator learning models.
method Constructive comparison between routed mixtures of neural operators (MoNOs) and a fixed single-neural-operator construction.
result Every scalar uniformly continuous nonlinear operator can be approximated by a MoNO whose active expert has smaller depth, width, and rank scaling.
Artificial neural networks typically have a fixed, non-linear activation function at each neuron. We have designed a novel form of piecewise linear activation function that is learned independently for each neuron using gradient descent. With this adaptive activation function, we are able to improve upon deep neural ne…
Neural networks approximate unit spheres as polytopes.
problem Approximating unit spheres with neural networks.
method Using ReLU activation in neural networks to generate polytopes.
result Neural networks can approximate unit spheres as polytopes.
Sparse activations in neural networks are hard to exploit but lead to advantages in learning.
problem Sparse activations in neural networks are hard to exploit but lead to advantages in learning.
method Formal study of PAC learnability of MLP layers with activation sparsity.
result Classes of functions with activation sparsity lead to provable computational and statistical advantages over their non-sparse counterparts.
The representations learned by deep neural networks are difficult to interpret in part due to their large parameter space and the complexities introduced by their multi-layer structure. We introduce a method for computing persistent homology over the graphical activation structure of neural networks, which provides acc…
Neural Galerkin schemes use active learning to solve high-dimensional equations.
problem Inaccurate function approximations in high dimensions with limited training data.
method Neural Galerkin schemes based on deep learning with active learning for high-dimensional PDEs.
result Active data collection improves the numerical solution of high-dimensional equations.
Learning automatically the best activation function for the task is an active topic in neural network research. At the moment, despite promising results, it is still difficult to determine a method for learning an activation function that is at the same time theoretically simple and easy to implement. Moreover, most of…
Visualizes DNNs using topographic maps for better understanding.
problem Difficulty in understanding how DNNs solve tasks.
method Adapting neuroscience methods to visualize DNN activations.
result Improved transparency and interpretability of DNN-based systems.
Active learning introduces bias; this paper fixes it.
problem Bias in active learning due to non-representative training data.
method Formalized bias, identified situations where it's harmful/helpful, introduced corrective weights.
result Corrective weights can improve active learning, especially with overparameterized models.
Early stopping in meta-learning improved by analyzing neural activation patterns.
problem Early stopping in few-shot learning is challenging due to distributional shifts between meta-validation and meta-test sets.
method Activation-Based Early-stopping (ABE) analyzes hidden layer activations from unlabelled support examples to detect when target generalization diverges from source data.
result Simple activation statistics can effectively estimate target generalization, improving few-shot transfer learning across various algorithms and datasets.
Smooth activations enable optimal error rates in neural networks for Sobolev function classes.
problem Achieving optimal approximation and estimation error rates for neural networks in Sobolev function classes.
method Study of neural networks with smooth activations, proving optimal rates via approximation and statistical properties.
result Constant-depth networks with smooth activations achieve optimal rates of approximation and estimation, demonstrating smoothness adaptivity.
New method trains neural networks with threshold activation functions efficiently.
problem Training neural networks with threshold activation functions is challenging due to zero gradients.
method We study weight decay regularized training problems of deep neural networks with threshold activations, showing they can be formulated as convex optimization problems.
result Regularized deep threshold network training problems can be formulated as standard convex optimization problems, paralleling the LASSO method.
ASEs use surrogate estimation to efficiently evaluate model performance with minimal labels.
problem Efficient model evaluation with limited labels.
method Surrogate-based estimation and active learning.
result ASEs offer greater label-efficiency than current methods for deep neural networks.
Wasserstein active regression improves estimation precision.
problem Improving regression model accuracy through active learning.
method Combines Wasserstein distance and GroupSort Neural Networks for uncertainty quantification.
result Wasserstein active regression often provides more precise estimations.
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.
Identifies learning rules from neural network observables.
problem Determine the underlying plasticity rules governing learning in biological systems.
method Simulated idealized neuroscience experiments with artificial neural networks to generate a dataset of learning trajectories. Used linear and non-linear classifiers to identify learning rules from aggregate statistics of weights, activations, and activity changes.
result Different classes of learning rules can be separated solely on the basis of aggregate statistics of the weights, activations, or instantaneous layer-wise activity changes.
This work simplifies Bayesian inference for neural networks by identifying influential parameter directions.
problem High computational complexity in Bayesian inference for neural networks due to high-dimensional parameter space.
method Constructing an active subspace of influential parameter directions to reduce dimensionality.
result Effective and scalable Bayesian inference achieved via reduced active subspace.
Survey of trainable activation functions in neural networks.
problem Improving neural network performance through trainable activation functions.
method Taxonomy and comparison of recent and past models of trainable activation functions.
result Many trainable activation functions are equivalent to adding neuron layers with fixed activation functions and simple constraints.
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation functio…
AReLU uses attention-based rectification to improve neural network performance.
problem Improving neural network performance through better activation functions.
method Integrates attention mechanism with rectified linear unit (ReLU) to learn and scale feature maps.
result AReLU significantly boosts performance of most network architectures with minimal changes.
Novel active learning framework using sparse approximation for efficient model training.
problem Efficient model training with limited labeled data.
method Formulates batch active learning as sparsity-constrained discontinuous optimization problems, using greedy or proximal iterative hard thresholding algorithms.
result Achieves competitive performance with lower computational complexity across different settings.
Automatically discovers effective activation functions for deep learning.
problem Inconsistent performance of novel activation functions in deep learning networks.
method Evolutionary search for general form, gradient descent for parameters.
result Significant performance improvements over ReLU and other functions.
Paper extends Chernoff sampling for active testing and parameter estimation, improving neural network and regression models.
problem Reducing sample complexity in hypothesis testing and model parameter estimation.
method Developed an extension of Chernoff sampling for active learning and parameter estimation.
result Non-asymptotic bounds for sample complexity and estimation error in active learning.
New method reduces version space for CNNs, improving active learning performance.
problem Sampling bias in active learning hinders optimal hypothesis finding in neural networks.
method Version space reduction through prior mass reduction and diameter reduction, proposing a new Gibbs-vote disagreement method.
result Diameter-based querying method reduces version space more effectively than prior mass reduction and other methods.
New method uses trainable activations to make BNNs behave like GPs.
problem Making Bayesian Neural Networks (BNNs) behave like Gaussian Processes (GPs).
method Introduced trainable activations and periodic activations to map GP priors to BNNs. Used 2-Wasserstein distance for optimization.
result Method consistently outperforms existing approaches or matches heuristic methods.
Improved neural active learning algorithms reduce regret and improve performance.
problem Improving performance and reducing regret in neural active learning for non-parametric streaming data.
method Introducing two new regret metrics and leveraging NNs for both exploitation and exploration. The algorithm uses tailored query decision-makers and full feedback.
result Achieved an instance-dependent regret upper bound improving by a multiplicative factor of O(logT) and removing the curse of dimensionality.