This paper investigates deep learning from a physics-informed perspective, examining its key features and surprises.

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…

Sublinearly structured DNNs achieve feature-learning and prediction consistency comparable to classical models

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 introduces Neural Expansion, a framework that explains deep neural network generalization through the expansion of directionally-selective ray coverage in the input space.

This paper proposes a deep-unfolding framework, Deep Coordinator, to dynamically adjust hyperparameters of a distributed solver for robotics tasks.

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

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 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…

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 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…

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…

A new spiking neural network design is proposed to process static images and event streams using time-to-first-spike latencies.

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…

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…