Articles in 2022

The combination of object recognition and viewpoint estimation is essential for visual understanding. However, convolutional neural networks often fail to generalize to object category–viewpoint combinations that were not seen during training. The authors investigate the impact of data diversity and architectural choices on the capability of generalizing to out-of-distribution combinations.

Controllers for robotic locomotion patterns deal with complex interactions and need to be carefully designed or extensively trained. Thor and Manoonpong present a modular approach for neural pattern generators that allows incremental and fast learning.

The investigation of single-cell epigenomics with technologies such as single-cell chromatin accessibility sequencing (scCAS) presents an opportunity to expand the understanding of gene regulation at the cellular level. The authors develop a probabilistic generative model to better characterize cell heterogeneity and accurately annotate the cell type of scCAS data.

Molecules are often represented as topological graphs while their true three-dimensional geometry contains a lot of valuable information. Xiaomin Fang and colleagues present a self-supervised molecule representation method that uses this geometric data in graph neural networks to predict a range of molecular properties.

Piezoresistors can be used in strain sensors for soft machines, but the traditional design process relies on intuition and human ingenuity alone. Haitao Yang and colleagues present a method built on genetic algorithms and other machine learning methods to design and fabricate strain sensors with improved capabilities.

Neural networks have become a useful approach for predicting biological function from large-scale DNA and protein sequence data; however, researchers are often unable to understand which features in an input sequence are important for a given model, making it difficult to explain predictions in terms of known biology. The authors introduce scrambler networks, a feature attribution method tailor-made for discrete sequence inputs.

In artificial neural networks, a typical neuron generally performs a simple summation of inputs. Using computational and electrophysiological data, the authors show that a single neuron predicts its future activity. Neurons that predict their own future responses are a potential mechanism for learning in the brain and neural networks.

Routine eye clinic imaging could help screen patients with cardiovascular risk as studies indicate strong associations between biomarkers in the retina and the heart. This potential is supported by a multimodal study, employing a deep learning model, that can infer cardiac functional indices based on retinal images and demographic data.

To train machine learning models for medical imaging, large amounts of training data are needed. Zhou and colleagues instead propose a method of weak supervision which uses the information of radiology reports to learn visual features without the need for expert labelling.

Reinforcement learning has shown remarkable success in areas such as game-playing and protein folding, but it has not been extensively explored in modelling cell behaviour. The authors develop an approach that uses deep reinforcement learning to uncover collective cell behaviours and the underlying mechanism of cell migration from 3D time-lapse images of tissues.