Articles

Brain–machine interfaces using steady-state visually evoked potentials (SSVEPs) show promise in therapeutic applications. With a combination of innovations in flexible and soft electronics and in deep learning approaches to classify potentials from two channels and from any subject, a compact, wireless and universal SSVEP interface is designed. Subjects can operate a wheelchair in real time with eye movements while wearing the new brain–machine interface.

A combination of engineering advances shows promise for myoelectric prosthetic hands that are controlled by a user’s remaining muscle activity. Fine finger movements are decoded from surface electromyograms with machine learning algorithms and this is combined with a robotic controller that is active only during object grasping to assist in maximizing contact. This shared control scheme allows user-controlled movements when high dexterity is desired, but also assisted grasping when robustness is required.

Memristive devices can provide energy-efficient neural network implementations, but they must be tailored to suit different network architectures. Wang et al. develop a trainable weight-sharing mechanism for memristor-based CNNs and ConvLSTMs, achieving a 75% reduction in weights without compromising accuracy.

Controlling the flow and representation of information in deep neural networks is fundamental to making networks intelligible. Bergomi et al introduce a mathematical framework in which the space of possible operators representing the data is constrained by using symmetries. This constrained space is still suitable for machine learning: operators can be efficiently computed, approximated and parameterized for optimization.

An approach to protein structure prediction is to assemble candidate structures from template fragments, which are extracted from known protein structures. Wang et al. demonstrate that combining deep neural network architectures with a relatively small but high-resolution fragment dataset can improve the quality of the sample fragment libraries used for protein structure prediction.

When neural networks are retrained to solve more than one problem, they tend to forget what they have learned earlier. Here, the authors propose orthogonal weights modification, a method to avoid this so-called catastrophic forgetting problem. Capitalizing on such an ability, a new module is introduced to enable the network to continually learn context-dependent processing.

Deep neural networks can contain arbitrary mathematical operators, as long as they are derivable. The authors investigate how knowledge about a problem can be incorporated into machine learning through the use of operators that are related to the problem.

For some combinatorial puzzles, solutions can be verified to be optimal, for others, the state space is too large to be certain that a solution is optimal. A new deep learning based search heuristic performs well on the iconic Rubik’s cube and can also generalize to puzzles in which optimal solvers are intractable.

Classifying individual responses in open-ended surveys can be subjective and time-consuming. A network-based survey framework automatically classifies responses in a statistically principled manner.

Neural networks are a promising digital pathology tool but are often criticized for their limited explainability. Faust and others demonstrate how machine-learned features correlate with human-understandable histological patterns and groupings, permitting increased transparency of deep learning tools in medicine.

Artificial intelligence approaches can aid medicinal chemists to creatively look for new chemical entities with drug-like properties. A rule-based approach combined with a machine learning model was trained on successful synthetic routes described in chemical patent literature. This process produced computer-generated compounds that mimic known medicines.

Reducing the radiation dose for medical CT scans can provide a less invasive imaging method, but requires a method for reconstructing an image up to the image quality from a full-dose scan. In this article, Wang and colleagues show that the deep learning approach, combined with the feedback from radiologists, produces higher quality reconstructions than or similar to that using the current commercial methods.

High-throughput brain image registration methods that are independent of any pre-processing steps, and are robust under mild image transformations, could accelerate the study of region-specific changes in brain development. A deep learning-based method is therefore developed for automated registration through segmenting brain regions of interest with minimal human supervision.

Deep neural networks are a powerful tool for predicting protein function, but identifying the specific parts of a protein sequence that are relevant to its functions remains a challenge. An occlusion-based sensitivity technique helps interpret these deep neural networks, and can guide protein engineering by locating functionally relevant protein positions.

Diagnostic pathology currently requires substantial human expertise, often with high inter-observer variability. A whole-slide pathology method automates the prediction process and provides computer-aided diagnosis using artificial intelligence.

Accurate manoeuvring of autonomous aerial and aquatic robots requires detailed knowledge of the fluid forces, which can be challenging especially in turbulent water or air. A control method for autonomous underwater vehicles (AUVs) uses intelligent distributed sensing inspired by fish ‘lateral line’ sensing. This is used by many species of fish to feel the flow around them and respond instantly, before they are displaced by disturbances. An AUV designed with such a sensory shell similarly compensates for disturbances and has improved position tracking.

Clustering groups of cells in single-cell RNA sequencing datasets can produce high-resolution information for complex biological questions. However, it is statistically and computationally challenging due to the low RNA capture rate, which results in a high number of false zero count observations. A deep learning approach called scDeepCluster, which efficiently combines a model for explicitly characterizing missing values with clustering, shows high performance and improved scalability with a computing time increasing linearly with sample size.

Biomedical publications provide a rich and largely untapped source of knowledge. INtERAcT exploits word embeddings trained on a corpus of cancer-specific articles to estimate molecular interactions. The algorithm is able to reconstruct molecular pathways associated with ten cancer types, even in corpora of limited size.

Present day quantum technologies enable computations with tens and soon hundreds of qubits. A major outstanding challenge is to measure and benchmark the complete quantum state, a task that grows exponentially with the system size. Generative models based on restricted Boltzmann machines and recurrent neural networks can be employed to solve this quantum tomography problem in a scalable manner.

To perform complex tasks, robots need to learn the relationship between their bodies and dynamic environments. A biologically plausible approach to hardware and software design shows that a robotic tendon-driven limb can make effective movements based on a short period of learning.