The column titled "Time [s]" means We used the G-orbit average pooling for this work. QV AEs, and IOV AEs, the output is two Dense(256, 5) layers with linear activation functions. AUCROC and AUPRC are the areas underneath the entire ROC and PR curves, respectively. The color clouds correspond to defect classes. The colored clouds represent specific cell classes.

This paper presents an improved forward-backward splitting algorithm with two inertial parameters. It aims to find a point in the real Hilbert space at which the sum of a co-coercive operator and a maximal monotone operator vanishes. Under standard assumptions, our proposed algorithm demonstrates weak convergence. We present numerous experimental results to demonstrate the behavior of the developed algorithm by comparing it with existing algorithms in the literature for regression and data classification problems. Furthermore, these implementations suggest our proposed algorithm yields superior outcomes when benchmarked against other relevant algorithms in existing literature.

Federated Learning (FL) has emerged as a promising privacy-preserving collaborative model training paradigm without sharing raw data. However, recent studies have revealed that private information can still be leaked through shared gradient information and attacked by Gradient Inversion Attacks (GIA). While many GIA methods have been proposed, a detailed analysis, evaluation, and summary of these methods are still lacking. Although various survey papers summarize existing privacy attacks in FL, few studies have conducted extensive experiments to unveil the effectiveness of GIA and their associated limiting factors in this context. To fill this gap, we first undertake a systematic review of GIA and categorize existing methods into three types, i.e., \textit{optimization-based} GIA (OP-GIA), \textit{generation-based} GIA (GEN-GIA), and \textit{analytics-based} GIA (ANA-GIA). Then, we comprehensively analyze and evaluate the three types of GIA in FL, providing insights into the factors that influence their performance, practicality, and potential threats. Our findings indicate that OP-GIA is the most practical attack setting despite its unsatisfactory performance, while GEN-GIA has many dependencies and ANA-GIA is easily detectable, making them both impractical. Finally, we offer a three-stage defense pipeline to users when designing FL frameworks and protocols for better privacy protection and share some future research directions from the perspectives of attackers and defenders that we believe should be pursued. We hope that our study can help researchers design more robust FL frameworks to defend against these attacks.

The article is devoted to the study of neural networks with one hidden layer and a modified activation function for solving physical problems. A rectified sigmoid activation function has been proposed to solve physical problems described by the ODE with neural networks. Algorithms for physics-informed data-driven initialization of a neural network and a neuron-by-neuron gradient-free fitting method have been presented for the neural network with this activation function. Numerical experiments demonstrate the superiority of neural networks with a rectified sigmoid function over neural networks with a sigmoid function in the accuracy of solving physical problems (harmonic oscillator, relativistic slingshot, and Lorentz system).

In the field of formal verification, Neural Networks (NNs) are typically reformulated into equivalent mathematical programs which are optimized over. To overcome the inherent non-convexity of these reformulations, convex relaxations of nonlinear activation functions are typically utilized. Common relaxations (i.e., static linear cuts) of "S-shaped" activation functions, however, can be overly loose, slowing down the overall verification process. In this paper, we derive tuneable hyperplanes which upper and lower bound the sigmoid activation function. When tuned in the dual space, these affine bounds smoothly rotate around the nonlinear manifold of the sigmoid activation function. This approach, termed $\alpha$-sig, allows us to tractably incorporate the tightest possible, element-wise convex relaxation of the sigmoid activation function into a formal verification framework. We embed these relaxations inside of large verification tasks and compare their performance to LiRPA and $\alpha$-CROWN, a state-of-the-art verification duo.

In the relentless efforts in enhancing medical diagnostics, the integration of state-of-the-art machine learning methodologies has emerged as a promising research area. In molecular biology, there has been an explosion of data generated from multi-omics sequencing. The advent sequencing equipment can provide large number of complicated measurements per one experiment. Therefore, traditional statistical methods face challenging tasks when dealing with such high dimensional data. However, most of the information contained in these datasets is redundant or unrelated and can be effectively reduced to significantly fewer variables without losing much information. Dimensionality reduction techniques are mathematical procedures that allow for this reduction; they have largely been developed through statistics and machine learning disciplines. The other challenge in medical datasets is having an imbalanced number of samples in the classes, which leads to biased results in machine learning models. This study, focused on tackling these challenges in a neural network that incorporates autoencoder to extract latent space of the features, and Generative Adversarial Networks (GAN) to generate synthetic samples. Latent space is the reduced dimensional space that captures the meaningful features of the original data. Our model starts with feature selection to select the discriminative features before feeding them to the neural network. Then, the model predicts the outcome of cancer for different datasets. The proposed model outperformed other existing models by scoring accuracy of 95.09% for bladder cancer dataset and 88.82% for the breast cancer dataset.

In this paper, we first identify activation shift, a simple but remarkable phenomenon in a neural network in which the preactivation value of a neuron has non-zero mean that depends on the angle between the weight vector of the neuron and the mean of the activation vector in the previous layer. We then propose linearly constrained weights (LCW) to reduce the activation shift in both fully connected and convolutional layers. The impact of reducing the activation shift in a neural network is studied from the perspective of how the variance of variables in the network changes through layer operations in both forward and backward chains. We also discuss its relationship to the vanishing gradient problem. Experimental results show that LCW enables a deep feedforward network with sigmoid activation functions to be trained efficiently by resolving the vanishing gradient problem. Moreover, combined with batch normalization, LCW improves generalization performance of both feedforward and convolutional networks.

Neural networks have proven to be a highly effective tool for solving complex problems in many areas of life. Recently, their importance and practical usability have further been reinforced with the advent of deep learning. One of the important conditions for the success of neural networks is the choice of an appropriate activation function introducing non-linearity into the model. Many types of these functions have been proposed in the literature in the past, but there is no single comprehensive source containing their exhaustive overview. The absence of this overview, even in our experience, leads to redundancy and the unintentional rediscovery of already existing activation functions. To bridge this gap, our paper presents an extensive survey involving 400 activation functions, which is several times larger in scale than previous surveys. Our comprehensive compilation also references these surveys; however, its main goal is to provide the most comprehensive overview and systematization of previously published activation functions with links to their original sources. The secondary aim is to update the current understanding of this family of functions.

Artificial neural networks (ANNs) with recurrence and self-attention have been shown to be Turing-complete (TC). However, existing work has shown that these ANNs require multiple turns or unbounded computation time, even with unbounded precision in weights, in order to recognize TC grammars. However, under constraints such as fixed or bounded precision neurons and time, ANNs without memory are shown to struggle to recognize even context-free languages. In this work, we extend the theoretical foundation for the $2^{nd}$-order recurrent network ($2^{nd}$ RNN) and prove there exists a class of a $2^{nd}$ RNN that is Turing-complete with bounded time. This model is capable of directly encoding a transition table into its recurrent weights, enabling bounded time computation and is interpretable by design. We also demonstrate that $2$nd order RNNs, without memory, under bounded weights and time constraints, outperform modern-day models such as vanilla RNNs and gated recurrent units in recognizing regular grammars. We provide an upper bound and a stability analysis on the maximum number of neurons required by $2$nd order RNNs to recognize any class of regular grammar. Extensive experiments on the Tomita grammars support our findings, demonstrating the importance of tensor connections in crafting computationally efficient RNNs. Finally, we show $2^{nd}$ order RNNs are also interpretable by extraction and can extract state machines with higher success rates as compared to first-order RNNs. Our results extend the theoretical foundations of RNNs and offer promising avenues for future explainable AI research.