Volume 2 Issue 1, January 2022

An adaptive and computationally efficient machine-learning-based biasing technique for rare-event sampling is introduced, allowing an effective generation of high-dimensional free energy surfaces associated with complex processes, such as protein folding.

Integrating multi-modal features is challenging due to the differences in the underlying distributions of each data type and the nonlinear associations across modalities. The deepManReg model improves the identification and interpretability of associations between modalities defining complex phenotypes.

There is still a wide variety of challenges that restrict the rapid growth of neuromorphic algorithmic and application development. Addressing these challenges is essential for the research community to be able to effectively use neuromorphic computers in the future.

The authors have developed an adaptive reinforced dynamics approach, which improves the efficiency when exploring the configurational space and free energy landscape of large biomolecules, such as proteins.

Tensor networks exploit the structure of turbulence to offer a compressed description of flows, which leads to efficient fluid simulation algorithms that can be implemented on both classical and quantum computers.

deepManReg uses deep neural networks to map various data types onto a topological space (manifolds) and unfold unseen data connections, thus improving prediction of phenotypes from multi-modal data.

The authors present an open-source framework that enables fast and accurate time–frequency analysis of signals and demonstrate it on real-world applications, such as signals from the brain–computer interface.