arXiv research

Sigmoid autoencoders can implement associative memory with certain conditions.

We develop a new approach to learn the parameters of regression models with hidden variables. In a nutshell, we estimate the gradient of the regression function at a set of random points, and cluster the estimated gradients. The centers of the clusters are used as estimates for the parameters of hidden units. We justif…

Improved logistic MoE with sigmoid gate shows better sample efficiency.

Sigmoid gating is more sample efficient than softmax in mixture of experts.

Study shows MSE with sigmoid can match SCE in classification tasks, especially with noisy data.

SummaryNet automates video summarisation using deep learning.

In this paper, we develop an alternating direction method of multipliers (ADMM) for deep neural networks training with sigmoid-type activation functions (called \textit{sigmoid-ADMM pair}), mainly motivated by the gradient-free nature of ADMM in avoiding the saturation of sigmoid-type activations and the advantages of …

We present a method for training multi-label, massively multi-class image classification models, that is faster and more accurate than supervision via a sigmoid cross-entropy loss (logistic regression). Our method consists in embedding high-dimensional sparse labels onto a lower-dimensional dense sphere of unit-normed …

Balanced Activation improves object detection performance on long-tailed datasets.

Sigmoid-type networks avoid vanishing gradients with regularization and rescaling.

Single tree outperforms random forest in testing accuracy.

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 $n$ …

New method initializes sigmoidal MLPs for interpretable shapes.

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…

S-GAI initializes MLPs using spectral geometry from data, improving performance.

The study optimizes polynomial regression for learning under Gaussian distributions.

DeepSeekMoE improves language model efficiency with shared experts and normalized gating.

We study layered neural networks of rectified linear units (ReLU) in a modelling framework for stochastic training processes. The comparison with sigmoidal activation functions is in the center of interest. We compute typical learning curves for shallow networks with K hidden units in matching student teacher scenarios…

SIGTRON improves classification accuracy for imbalanced datasets.

New ACE cost function encourages diversity in neural networks.

Long Short-Term Memory (LSTM) infers the long term dependency through a cell state maintained by the input and the forget gate structures, which models a gate output as a value in [0,1] through a sigmoid function. However, due to the graduality of the sigmoid function, the sigmoid gate is not flexible in representing m…

In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural netw…

Deep conditional generative models are developed to simultaneously learn the temporal dependencies of multiple sequences. The model is designed by introducing a three-way weight tensor to capture the multiplicative interactions between side information and sequences. The proposed model builds on the Temporal Sigmoid Be…

We simplify word embeddings by removing sigmoid in SGNS, revealing connections to hyperbolic spaces.

Investigates least squares estimation in deterministic MoE models.

We show that any smooth bi-Lipschitz $h$ can be represented exactly as a composition $h_m \circ ... \circ h_1$ of functions $h_1,...,h_m$ that are close to the identity in the sense that each $\left(h_i-\mathrm{Id}\right)$ is Lipschitz, and the Lipschitz constant decreases inversely with the number $m$ of functions com…

Deep dynamic generative models are developed to learn sequential dependencies in time-series data. The multi-layered model is designed by constructing a hierarchy of temporal sigmoid belief networks (TSBNs), defined as a sequential stack of sigmoid belief networks (SBNs). Each SBN has a contextual hidden state, inherit…

We propose a differentiable sigmoid function for efficient p-value calculation in clustering.

Improved learning bounds for corrupted data using thresholded gradient descent.

The article compares neural networks and logistic regression for credit scoring and introduces a new probability calibration technique.

Lower bound proves ridgeless regression performs poorly near interpolation threshold.

Survival trees exhibit end-cut preference, leading to biased splits.

Randomized methods of neural network learning suffer from a problem with the generation of random parameters as they are difficult to set optimally to obtain a good projection space. The standard method draws the parameters from a fixed interval which is independent of the data scope and activation function type. This …

We introduce exact macroscopic on-line learning dynamics of two-layer neural networks with ReLU units in the form of a system of differential equations, using techniques borrowed from statistical physics. For the first experiments, numerical solutions reveal similar behavior compared to sigmoidal activation researched …

GLU variants improve Transformer performance.

There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the approximation ability of deep neural networks with a broad class of activation functi…

Optimal neuron activation functions improve neural network performance.

A new model predicts race places using changeover-times and log-normal distributions.

Guiding the design of neural networks is of great importance to save enormous resources consumed on empirical decisions of architectural parameters. This paper constructs shallow sigmoid-type neural networks that achieve 100% accuracy in classification for datasets following a linear separability condition. The separab…

Assessing heterogeneous treatment effects has become a growing interest in advancing precision medicine. Individualized treatment effects (ITE) play a critical role in such an endeavor. Concerning experimental data collected from randomized trials, we put forward a method, termed random forests of interaction trees (RF…

Tempered sigmoids improve deep learning privacy.

New bounds show complex neural networks need many queries to learn.

The study explores how Matrix Product States can represent boolean and continuous functions.

In this paper, we prove that a shallow neural network with a monotone sigmoid, ReLU, ELU, Softplus, or LeakyReLU activation function can arbitrarily well approximate any L^p(p>=2) integrable functions defined on R*[0,1]^n. We also prove that a shallow neural network with a sigmoid, ReLU, ELU, Softplus, or LeakyReLU act…

Proposes a method to visualize finer cluster structures in high-dimensional data.

We consider network sparsification as an $L_0$-norm regularized binary optimization problem, where each unit of a neural network (e.g., weight, neuron, or channel, etc.) is attached with a stochastic binary gate, whose parameters are jointly optimized with original network parameters. The Augment-Reinforce-Merge (ARM),…

Paper investigates differentiable fuzzy implications and their suitability for learning.

This note is concerned with accurate and computationally efficient approximations of moments of Gaussian random variables passed through sigmoid or softmax mappings. These approximations are semi-analytical (i.e. they involve the numerical adjustment of parametric forms) and highly accurate (they yield 5% error at most…