Activation functions have a notorious impact on neural networks on both training and testing the models against the desired problem. Currently, the most used activation function is the Rectified Linear Unit (ReLU). This paper introduces a new and novel activation function, closely related with the new activation $Swish…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Swish activation”
LSQ+ improves quantization of neural nets with Swish activations, achieving state-of-the-art results.
problem Quantization of neural nets with Swish activations, especially negative activations, leads to significant performance loss.
method Introduces learnable scale and offset parameters for asymmetric quantization, and uses MSE-based initialization for quantization parameters.
result Significantly outperforms LSQ for low-bit quantization of neural nets with Swish activations, achieving up to 5.6% gain with W2A2 quantization of EfficientNet-B0.
This work interprets GELU and related activations via a first-order loss function.
problem Understanding and optimizing activation functions in neural networks.
method Complementary interpretation using the Gaussian first-order loss function.
result Calibrated or learned uniform-threshold gates are competitive and often outperform GELU, ReLU, and SiLU/Swish.
Activation functions are essential for deep learning methods to learn and perform complex tasks such as image classification. Rectified Linear Unit (ReLU) has been widely used and become the default activation function across the deep learning community since 2012. Although ReLU has been popular, however, the hard zero…
The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward propagation and the exponential vanishing/exploding of gradients during back-propag…
Highly Accurate CNN Inference Using Approximate Activation Functions over Homomorphic Encryptioncs.LG
Improved CNN accuracy for encrypted data using approximate activation functions.
problem Low accuracy in classifying encrypted data using homomorphic encryption.
method Used a fourth-order polynomial approximation of the Swish activation function with batch normalization for homomorphic encryption.
result Achieved 99.22% accuracy on MNIST and 80.48% on CIFAR-10, improving by 0.04% and 4.11% respectively.
We present a Statistical Mechanics (SM) model of deep neural networks, connecting the energy-based and the feed forward networks (FFN) approach. We infer that FFN can be understood as performing three basic steps: encoding, representation validation and propagation. From the meanfield solution of the model, we obtain a…
Study learns a neuron with non-monotonic activation functions.
problem Learning a single neuron with non-monotonic activation functions.
method Gradient descent (GD) with conditions on activation function and input distribution.
result Learnability of non-monotonic activation functions is established without monotonicity assumption.
Deep networks can approximate various activation functions with modest adjustments.
problem Expressive power of deep neural networks with diverse activation functions.
method Approximation of any activation function in set A by ReLU networks with specific scaling factors.
result Approximation of any activation function in a specific subset of A by ReLU networks with (1,1) scaling factors.
An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification learning methods like (generalized) learning vector quantization (GLVQ) are powerful…
Study uses 1D-CNNs to forecast mortality in ELSA survey.
problem Forecasting mortality in the middle-aged and older population.
method 1D-CNNs applied to longitudinal data with various over/undersampling and activation functions.
result Swish nonlinearity outperforms other functions in forecasting mortality.
An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore what happens when the…
This paper proposes an embedding-based neural network for more accurate investment return prediction.
problem Accurately predicting investment returns requires understanding industry knowledge and news, as well as leveraging relevant theories.
method The approach uses embedding to encode investment IDs into low-dimensional vectors, leveraging dual branches to separate different information, and employs the swish activation function.
result The proposed embedding-based dual branch model outperforms traditional machine learning models like Xgboost, Lightgbm, and Catboost on the Ubiquant Market Prediction dataset.
Gradient descent with logistic loss can interpolate deep networks with smoothed ReLU activations under certain conditions.
problem Conditions for gradient descent to drive logistic loss to zero in deep networks with smoothed ReLU activations.
method Gradient descent applied to fixed-width deep networks with smoothed ReLU approximations (e.g., Swish, Huberized ReLU).
result Gradient descent can drive logistic loss to zero under specific conditions, providing bounds on convergence rate.
We propose , a novel self-regularized non-monotonic activation function which can be mathematically defined as: . As activation functions play a crucial role in the performance and training dynamics in neural networks, we validated experimentally on several well-known benchmarks…
New method improves ResNet performance without batch normalization.
problem Improving ResNet performance without batch normalization.
method Adapted Weight Standardization to maintain signal propagation.
result Highly performant ResNets achieve state-of-the-art performance on ImageNet.
We propose K-TanH, a novel, highly accurate, hardware efficient approximation of popular activation function TanH for Deep Learning. K-TanH consists of parameterized low-precision integer operations, such as, shift and add/subtract (no floating point operation needed) where parameters are stored in very small look-up t…
In order to classify linearly non-separable data, neurons are typically organized into multi-layer neural networks that are equipped with at least one hidden layer. Inspired by some recent discoveries in neuroscience, we propose a new model of artificial neuron along with a novel activation function enabling the learni…
It is well-known that overparametrized neural networks trained using gradient-based methods quickly achieve small training error with appropriate hyperparameter settings. Recent papers have proved this statement theoretically for highly overparametrized networks under reasonable assumptions. These results either assume…
Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently incorporate normalization based on central limit theory. SELU is a monotonically incre…
This paper explores adversarial training limits and improves model robustness against norm-bounded perturbations.
problem Understanding and improving adversarial robustness of deep neural networks.
method Systematic study of adversarial training with various factors, including model size, activation functions, and unlabeled data.
result Training robust models that go beyond state-of-the-art results by combining larger models, Swish/SiLU activations, and model weight averaging.
Geometric theory of projection heads in self-supervised learning.
problem Dimensional collapse and information invariance trade-off in projection heads.
method Geometric modeling of projection heads as Riemannian metrics, analyzing Hessian eigenvalues, and tracking optimization geometry.
result Smooth nonlinear heads induce negative curvature, preventing collapse; linear and ReLU heads cannot.
Nonlinearity is crucial to the performance of a deep (neural) network (DN). To date there has been little progress understanding the menagerie of available nonlinearities, but recently progress has been made on understanding the rôle played by piecewise affine and convex nonlinearities like the ReLU and absolute value …
This paper precisely estimates transformer derivatives for explicit learning guarantees.
problem Computing fully-explicit generalization bounds for transformers with precise higher-order derivative estimates.
method Analyzes and estimates all higher-order derivatives of transformers with multiple attention heads and layer normalization.
result Obtains explicit pathwise generalization bounds for transformers learning from non-i.i.d. samples.
New self-exciting random evolutions (SEREs) for modeling traffic and transport processes.
problem Modeling self-exciting and clustering effects in traffic and transport processes.
method Introducing a new process based on a superposition of a Markov chain and a Hawkes process, and constructing self-exciting random evolutions (SEREs).
result Developed new models and limit theorems for SEREs, including averaging and diffusion approximation.
Many activation functions have been proposed in the past, but selecting an adequate one requires trial and error. We propose a new methodology of designing activation functions within a neural network at each layer. We call this technique an "activation ensemble" because it allows the use of multiple activation functio…
This paper studies activation sparsity in large language models, finding key trends and implications.
problem Activation sparsity in large language models (LLMs) can be improved for efficiency and interpretability.
method Proposes PPL- sparsity, analyzes trends with training data, width-depth ratio, and parameter scale.
result ReLU is more efficient for sparsity than SiLU, and deeper architectures can improve sparsity.
Activity recognition from sensor data deals with various challenges, such as overlapping activities, activity labeling, and activity detection. Although each challenge in the field of recognition has great importance, the most important one refers to online activity recognition. The present study tries to use online hi…
Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the activation, and the weights capture the scale. Here we propose to train the netw…
Active learning method balances bias and variance under class imbalance.
problem Active learning under label shift when class proportions differ.
method Mediated Active Learning under Label Shift (MALLS) using a 'medial distribution'.
result MALLS reduces asymptotic sample complexity under arbitrary label shift.
Study active learning of PTFs with derivative access.
problem Active learning of polynomial threshold functions (PTFs).
method Algorithm for active learning degree- univariate PTFs with derivative access.
result Computational efficient algorithm for active learning degree- univariate PTFs.
Collaborative filtering is a useful technique for exploiting the preference patterns of a group of users to predict the utility of items for the active user. In general, the performance of collaborative filtering depends on the number of rated examples given by the active user. The more the number of rated examples giv…
Characterizing the robustness of Bayesian adaptive experimental designs to active learning biasstat.ME
Bayesian adaptive designs can be biased by active learning, especially with misspecified models.
problem Active learning bias in Bayesian adaptive experimental designs.
method Analysis of linear and preference learning models, empirical testing.
result Model misspecification and noise influence active learning bias in Bayesian designs.
Derives time-averaged active inference from control principles.
problem Finite-horizon or discounted-surprise problems in active inference.
method Derives infinite-horizon, average-surprise active inference from optimal control principles.
result Unified objective functional for sensorimotor control.
RAN model recognizes multiple activities from unlabeled sensor data.
problem Handling weakly labeled multi-activity data from wearable sensors.
method Recurrent Attention Networks (RAN) for sequential multi-activity recognition and localization.
result RAN model can infer multiple activities and determine activity locations from unlabeled data.
A new indicator measures project risk from activity durations.
problem Managing project risks throughout the lifecycle.
method Activity Risk Index (ARI) based on Schedule Risk Baseline.
result Identifies activities contributing most to project uncertainty.
Hidden Markov Models detect hand gestures from wearable sEMG signals.
problem Detecting activity regions in continuous sEMG signals.
method Hidden Markov Models applied to sEMG signals for gesture recognition.
result Average accuracy of 96.25% for activity onsets and 87.5% for activity terminations.
Active testing reduces label costs for efficient model evaluation.
problem Real-world applications require expensive test labels, disconnecting from existing model evaluation methods.
method Derives acquisition strategies to select test points efficiently, addressing label bias and variance.
result Active testing improves model evaluation efficiency without sacrificing accuracy.
The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, the Rectified Linear Unit (ReLU) remains the most commonly-used in practice. This paper shows that evolutionary algorithms can discover novel…
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.
This paper analyzes and improves active learning techniques for real-world projects.
problem Reducing labelling effort in machine learning models with real-world constraints.
method Systematic study of active learning issues, proposing techniques to address model convergence, annotation error, and dataset imbalance.
result Presentation of two techniques to speed up active learning: partial uncertainty sampling and larger query size.
Active nematodynamics on deformable surfacescond-mat.soft
Study active nematic forces on curved surfaces, revealing new coupling mechanisms.
problem Understanding active nematic forces on curved surfaces.
method Developed a thermodynamically consistent surface model with nematic activity, analyzed topological defects.
result Active defects contribute both tangential and normal forces on curved surfaces.
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.
Bayesian active learning method improved for censored regression data.
problem Challenges in estimating BALD for censored regression data.
method Derived entropy and mutual information for censored distributions, developed -BALD objective, proposed novel modelling approach.
result Demonstrated -BALD outperforms other methods in censored regression.
DUNs improve active learning by dynamically adjusting model complexity.
problem Active learning datasets grow, leading to model bias or overfitting.
method Depth Uncertainty Networks (DUNs) infer model depth for flexibility and complexity.
result DUNs outperform other BNN variants on active learning tasks, reducing overfitting.
Large deviation principle for deep neural networks with ReLU activation.
problem Understanding the behavior of deep neural networks with ReLU activation.
method Proving a large deviation principle for networks with Gaussian weights and ReLU activation functions.
result Simplified expressions and power-series expansions for the ReLU case.
TransFall uses transfer learning to improve activity recognition from mobile sensors.
problem Performance degradation due to platform and user movement differences.
method Two-tier data transformation, label estimation, and model generation layers.
result TransFall enhances activity recognition accuracy for new scenarios.
Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activation functions by setting them to be identity functions randomly during training time. During testing, …