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

This paper compares two theoretical frameworks for hierarchical neural networks with a finite but large number of hidden units and shows that training input-to-hidden weights reduces generalization er…

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…

This paper proposes Hierarchical Block-Local Learning (HBLL), a framework for training deep neural networks without full end-to-end backpropagation, achieving $\mathcal{O}(\log N)$ parallel time compl…

This paper provides the first algorithmic separation between constant-depth and logarithmic-depth networks, identifying a class of Boolean functions that logarithmic-depth networks can learn efficient…

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 characterizes the gap between neural network performance and their neural tangent kernel limit on compositional tasks, attributing it to a mismatch between kernel smoothness bias and target…

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 paper compares and optimizes CUDA strategies for a shallow neural network, achieving a 1.41x speedup on a large dataset.

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…

This paper explores how different components of the Transformer feedforward block architecture impact rank preservation across depth during initialization.

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…

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…

A new error backpropagation method called supervised counterstream learning is proposed for deep associative networks, which only requires recognition of errors during training and backpropagates corr…

This paper studies the expressivity of shallow polynomial neural networks with monomial activation functions over finite fields, quantifying it by the cardinality of the neuromanifold and deriving low…

This paper proves that the maximum of up to 10 real numbers can be exactly represented by a ReLU network with two hidden layers, and shows that the same depth bound holds for all continuous piecewise-…

The paper proposes using an auxiliary reconstruction task, specifically one that captures intra-state feature dependencies, to improve the quality of state representations learned by the encoder in ne…

The paper analyzes LLM vulnerability detection using mechanistic interpretability, finding that models primarily rely on safety detectors rather than direct vulnerability signature recognition.

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…