Neural Network

Neural networks are computational models inspired by the structure and function of the brain, primarily aimed at approximating complex functions and solving diverse problems through learning from data. Current research emphasizes improving efficiency and robustness, exploring novel architectures like sinusoidal neural fields and hybrid models combining neural networks with radial basis functions, as well as developing methods for understanding and manipulating the internal representations learned by these networks, such as through hyper-representations of network weights. These advancements are driving progress in various fields, including computer vision, natural language processing, and scientific modeling, by enabling more accurate, efficient, and interpretable AI systems.

Papers

June 5, 2024

Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers
Brian K Chen, Tianyang Hu, Hui Jin, Hwee Kuan Lee, Kenji Kawaguchi
Large Language Model Neural Network Context Learning Transformer Network Automated Conversion Linear Transformer Model Weight Linear Attention Transformer

June 4, 2024

June 3, 2024

June 1, 2024

May 31, 2024

Neural Network

Papers

Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers

Adaptive multiple optimal learning factors for neural network training

Ai-Sampler: Adversarial Learning of Markov kernels with involutive maps

Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks

nn2poly: An R Package for Converting Neural Networks into Interpretable Polynomials

Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit

Iteration over event space in time-to-first-spike spiking neural networks for Twitter bot classification

Physics-Informed Neural Networks for Dynamic Process Operations with Limited Physical Knowledge and Data

Predicting the fatigue life of asphalt concrete using neural networks

An efficient Wasserstein-distance approach for reconstructing jump-diffusion processes using parameterized neural networks

Hardness of Learning Neural Networks under the Manifold Hypothesis

Evidence of Learned Look-Ahead in a Chess-Playing Neural Network

Amalgam: A Framework for Obfuscated Neural Network Training on the Cloud

Gated recurrent neural network with TPE Bayesian optimization for enhancing stock index prediction accuracy

Empirical influence functions to understand the logic of fine-tuning

Activation-Descent Regularization for Input Optimization of ReLU Networks

Stochastic Restarting to Overcome Overfitting in Neural Networks with Noisy Labels

Real-Time State Modulation and Acquisition Circuit in Neuromorphic Memristive Systems

Verification of Neural Network Control Systems in Continuous Time

Aligning Multiclass Neural Network Classifier Criterion with Task Performance via $F_\beta$-Score