Sigmoid autoencoders can implement associative memory with certain conditions.
problem Implementing associative memory in neural networks.
method Theoretical analysis of overparameterized sigmoid autoencoders using the NTK and iterative maps.
result Overparameterized sigmoid autoencoders can have attractors in the NTK limit, leading to associative memory.
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.
problem Improving sample efficiency in logistic MoE models.
method Comprehensive analysis of multinomial logistic MoE with modified sigmoid gate, incorporating temperature parameter and using Euclidean score.
result The sigmoid gate leads to lower sample complexity than softmax gate for both parameter and expert estimation.
Sigmoid gating is more sample efficient than softmax in mixture of experts.
problem Softmax gating leads to unnecessary competition among experts, causing representation collapse.
method Theoretical analysis of a regression framework with mixture of experts, identifying identifiability conditions and convergence rates.
result Sigmoid gating requires fewer samples to achieve the same expert estimation error as softmax gating.
Study shows MSE with sigmoid can match SCE in classification tasks, especially with noisy data.
problem Inconsistent errors in neural network classification tasks.
method Introduced Output Reset algorithm to use MSE with sigmoid activation.
result MSE with sigmoid activation achieves comparable accuracy and convergence rates to Softmax Cross-Entropy, especially in noisy data scenarios.
SummaryNet automates video summarisation using deep learning.
problem Creating informative video summaries from videos.
method Two-stream convolutional network for spatial and temporal features, encoder-decoder model for salient features, sigmoid regression with LSTM for frame probability.
result SummaryNet achieves comparable or better results than state-of-the-art methods on benchmark datasets.
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.
problem Mismatch between training and testing label distributions in object detection.
method Introduces Balanced Activation (Balanced Softmax and Balanced Sigmoid) to address label distribution shift.
result Balanced Activation provides ~3% gain in mAP on LVIS-1.0 compared to state-of-the-art methods.
Sigmoid-type networks avoid vanishing gradients with regularization and rescaling.
problem Vanishing gradients in sigmoid-type networks.
method Mathematical arguments and two remedies: regularization and rescaling.
result Demonstrates effectiveness of regularization and rescaling in practice.
Single tree outperforms random forest in testing accuracy.
problem The challenge of improving single decision tree performance.
method Gradient-based entire tree optimization framework, scaled sigmoid approximation, numerical stability algorithm, subtree polish strategy.
result Optimized single tree outperforms classic random forest by 2.03% on average.
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.
problem Creating interpretable decision boundaries in neural networks.
method Introducing a geometry-aware initialization for sigmoidal multi-layer perceptrons (MLPs) using tropical geometry.
result Sigmoidal MLPs can have decision boundaries aligned with prescribed shapes at initialization.
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.
problem Lack of guidance on initial weights encoding data geometry.
method S-GAI uses SVD to estimate spectral class geometry, initializing MLPs from training data.
result S-GAI-initialized MLPs start from a more informative hidden state and achieve comparable accuracy.
The study optimizes polynomial regression for learning under Gaussian distributions.
problem Agnostic learning of Boolean and real-valued functions under Gaussian distributions.
method LP duality and polynomial degree analysis for L1-regression. result Optimal SQ lower bounds for various function classes.
DeepSeekMoE improves language model efficiency with shared experts and normalized gating.
problem Improving sample efficiency in language model architectures.
method Theoretical and empirical analysis of shared experts and normalized sigmoid gating.
result Theoretical and empirical evidence of improved sample 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.
problem Improving classification accuracy for imbalanced datasets.
method SIGTRON is a new sigmoid function with a convex loss function for imbalanced classification.
result SIGTRON models outperform existing methods in balanced and imbalanced datasets.
New ACE cost function encourages diversity in neural networks.
problem Training multiple classifiers with controlled diversity.
method Mathematical derivation and gradient control.
result ACE yields better ensemble results than vanilla.
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.
problem Improving word embeddings quality and understanding their relationship with hyperbolic spaces.
method Analyzing squashed shifted PMI matrix and its relation to graph properties and hyperbolic geometry.
result Word embeddings can be connected to hyperbolic spaces through squashed shifted PMI matrix.
Investigates least squares estimation in deterministic MoE models.
problem Complexity and difficulty in analyzing MoE models.
method Least squares estimation under deterministic MoE models.
result Rates of estimating strongly identifiable experts are faster than polynomial experts.
We show that any smooth bi-Lipschitz h can be represented exactly as a composition hm∘...∘h1 of functions h1,...,hm that are close to the identity in the sense that each (hi−Id) 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…
Improved learning bounds for corrupted data using thresholded gradient descent.
problem Learning from corrupted data with adversarial noise.
method Thresholded gradient descent for sigmoidal, leaky-ReLU, and ReLU activations.
result Improved approximation bounds for various activation functions.
We propose a differentiable sigmoid function for efficient p-value calculation in clustering.
problem Efficient and accurate p-value calculation for clustering algorithms.
method Designed a differentiable sigmoid function to approximate the Dip-p-value transformation.
result Accelerates computation and integrates well with gradient descent-based learning schemes.
The article compares neural networks and logistic regression for credit scoring and introduces a new probability calibration technique.
problem Improving credit scoring accuracy using machine learning techniques.
method Comparison of logistic regression and neural networks, feature importance assessment, temporal feature inclusion, and SURE probability calibration.
result Neural networks can slightly improve credit scoring performance, and SURE calibration technique enhances probability calibration.
Lower bound proves ridgeless regression performs poorly near interpolation threshold.
problem Proving performance of ridgeless regression near interpolation threshold.
method Distribution-independent lower bound for mean squared error in noisy ridgeless linear regression.
result Lower bound implies ridgeless regression performs poorly near interpolation threshold.
Survival trees exhibit end-cut preference, leading to biased splits.
problem End-cut preference in survival trees causes biased splits and poor interpretability.
method Proposed a smooth sigmoid surrogate (SSS) approach to replace hard-threshold indicator function.
result Smooth sigmoid surrogate (SSS) effectively mitigates end-cut preference in survival trees.
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.
problem Improving the performance of Transformer models.
method Tested variations of Gated Linear Units (GLU) in Transformer feed-forward sublayers.
result Some GLU variants yield better performance than ReLU or GELU activations.
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.
problem Limited expressive power of standard neuron activation functions in neural networks.
method Additive Gaussian process regression to construct individual neuron activation functions.
result Optimal neuron activation functions lead to better performance and reduced overfitting.
A new model predicts race places using changeover-times and log-normal distributions.
problem Predicting race places in orienteering races.
method Fenton-Wilkinson Order Statistics model based on log-normal leg-times and changeover-times.
result The model accurately predicts race places with smaller root-mean-square-errors.
We developed safe and ranged approximations for ReLU, tanh, and sigmoid functions to reduce neural network training time.
problem Expensive computation of hyperbolic tangent and sigmoid functions in neural networks.
method Function approximation techniques to create safe and ranged approximations.
result 10% to 37% improvement in training times on CPU and 20% to 53% improvement in ranged cases.
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.
problem Privacy-preserving deep learning with strict differential privacy guarantees.
method Developed tempered sigmoid activation functions for deep learning models.
result Tempered sigmoids outperform ReLU in achieving state-of-the-art accuracy.
Python scripts analyze MRAM-based neuromorphic devices' process variation impacts on machine learning accuracy.
problem Impact of process variation on MRAM-based neuromorphic devices' performance in machine learning applications.
method Developed transportable Python scripts to analyze output variation under changes in device dimensions.
result Revealed impacts and limits for processing variation of device fabrication on energy vs. accuracy tradeoffs.
Paper develops privacy-preserving mechanisms for machine learning using wavelet transforms.
problem Improper data privacy methods compromise user data even with small preliminary knowledge.
method Three privacy-preserving mechanisms with discrete M-band wavelet transform.
result Successfully retains both differential privacy and learnability in various machine learning environments.
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 2ncε queries. The study explores how Matrix Product States can represent boolean and continuous functions.
problem Representing arbitrary boolean and continuous functions using Matrix Product States.
method Developed a construction method for MPS to represent boolean gates and proved density in continuous function space.
result MPS can accurately represent arbitrary boolean functions and continuous functions densely.
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.
problem Visualization of high-dimensional data with complex cluster structures.
method Introduces a generalized sigmoid function with a parameter b to adjust the tail heaviness for better visualization.
result The method can generate visualization results comparable to UMAP, revealing finer cluster structures.