This paper investigates limitations of learning tanh neural networks under finite-precision computations and Lp accuracy guarantees.

This paper proposes a preconditioning layer for stable weight conditioning in LLM training.

This paper investigates whether deep learning models retain the phase/sign asymmetry of natural images in their hidden layers and tests it causally.

The paper analyzes congruence-based neural architectures for classifying positive-definite matrices, demonstrating that common semi-orthogonality constraints severely limit the model's expressivity.

This study empirically benchmarks classical and quantum machine learning models for image recognition, finding that while quantum models offer superior accuracy and resource efficiency at high dimensi…

This paper introduces a mechanistic neuronal network model for multilayer learning, offering biological insights and an alternative to backpropagation.

This paper analyzes the impact of long-term and short-term transistor aging on Deep Neural Network (DNN) inference accuracy and proposes an aging-aware retraining methodology to maintain performance e…

The paper introduces Dual-Spectral Flow Matching (DSFM), a novel generative framework that uses wavelet and cosine transforms to synthesize highly realistic, non-stationary fMRI time series for improv…

The paper introduces a novel, non-deep neural network architecture that achieves the performance of LLMs by finding the global optimum of the loss function in a single, closed-form iteration, eliminat…

This paper addresses the vulnerability of DNNs used in robotic semantic segmentation to adversarial attacks by proposing specialized detection strategies to enhance safety in robotic perception system…

The paper introduces Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) to achieve massive, structured compression of deep neural networks, demonstrating compression ratios up to 77,000x…

This study comparatively evaluates four CNN architectures (VGG16, ResNet50, EfficientNetB0, and XceptionNet) for fake image detection, finding VGG16 achieved the highest accuracy (91%).

This paper analyzes the computational complexity of verifying feedforward neural networks when their weights are restricted to finite-width arithmetic, finding that verification remains NP-complete fo…

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

The paper establishes that the training process of fully connected deep neural networks (DNNs) on exponential family data is mathematically equivalent to performing a Renormalization Group (RG) calcul…

This paper proposes a hybrid CNN-LSTM framework to enhance cyber attack detection and prevention in U.S. critical digital infrastructure by evaluating multiple machine learning models on the CSE-CIC-I…

The paper proposes an SE ViT-BiLSTM hybrid model for enhanced intrusion detection in IIoT and IoMT environments, achieving superior performance on real-world datasets, especially after data balancing.

This paper investigates a novel physical backdoor attack against Deep Automatic Modulation Classifiers (AMC) in wireless communications, demonstrating that an adversary using Explainable AI (XAI) can…

The paper introduces Morlet Positional Encoding (MoPE), a novel wavelet-based positional encoding that models position and locality simultaneously, outperforming standard sinusoidal and RoPE methods.