Luo, D. and Clark, B.K. (2019) Backflow Transformations via Neural Networks for Quantum Many-Body Wave Functions. Physical Review Letters, 122, Article 226401. Login ...

The learning capability of neural networks is equivalent to modeling physical events that occur in the real environment. Several early works have demonstrated that neural networks belonging to some ...

Inspired by microscopic worms, Liquid AI’s founders developed a more adaptive, less energy-hungry kind of neural network. Now the MIT spin-off is revealing several new ultraefficient models.

The optimization problem can be solved by the proposed neural network with good structural interpretability. The spatial construction method is employed to derive the continuous spatial basis ...

To address these limitations, in a new paper Composable Function-preserving Expansions for Transformer Architectures, a research team from Google DeepMind and University of Toulouse introduces ...

Some previous works have also proposed function-preserving parameter expansion transformations for transformer-based models, extending from techniques for smaller convolutional and dense models.

Activation functions for neural networks are an essential part of deep learning since they decide the accuracy and efficiency of the training model used to create or split a large-scale neural network ...