Articles

Persistent homology provides an efficient approach to simplifying the complexity of protein structure. Wang et al. combine this approach with convolutional neural networks and gradient-boosting trees to improve predictions of protein–protein interactions.

Age-related macular degeneration is a serious eye disease which should be detected as early as possible. Using both fundus images and genetic information, a deep neural network is able to detect the severity of the disease and predict its progression seven years into the future.

Counting different types of circulating tumour cells can give valuable information on the severity of the disease and on whether treatments are effective for a specific patient. In this work, the authors show that their method based on autoencoders can identify and count cells more accurately and faster than human experts.

The dynamics of paper shapes in free fall are still not fully understood, despite being discussed for more than 150 years. Collecting large amounts of data has the potential to give us new insights and a robotics system could generate and analyse data in large quantities.

Neural networks are often implemented with reduced precision in order to meet the tight energy and memory budget required by edge computing devices. Chakraborty et al. develop a technique for assessing which layers can be quantized, and by how much, without sacrificing too much on performance.

By assembling conceptual systems from real-word datasets of text, images and audio, Roads and Love propose that objects embedded within a conceptual system have a unique signature that allows for conceptual systems to be aligned in an unsupervised fashion.

Tree-based machine learning models are widely used in domains such as healthcare, finance and public services. The authors present an explanation method for trees that enables the computation of optimal local explanations for individual predictions, and demonstrate their method on three medical datasets.

Magnetic resonance scans use different contrast agents to generate different images, each giving specific clinical information. Lee et al. use a collaborative generative model to synthesize some magnetic resonance contrasts from others, providing guidance for how clinical imaging times can be reduced.

Predicting the structure of proteins from amino acid sequences is a hard problem. Convolutional neural networks can learn to predict a map of distances between amino acid residues that can be turned into a three-dimensional structure. With a combination of approaches, including an evolutionary technique to find the best neural network architecture and a tool to find the atom coordinates in the folded structure, a pipeline for rapid prediction of three-dimensional protein structures is demonstrated.

Number processing is linked to bodily systems, especially finger movements. The authors apply convolutional neural network models in the context of cognitive developmental robotics. They show that proprioceptive information in the child-like robot iCub improves accuracy and recognition of spoken digits.

Haptic interfaces are important for the development of immersive human–machine interactions. To create a compact design with rich touch-sensitive functions, a robotic device called Foldaway, which folds flat, has been designed that can render three-degrees-of-freedom force feedback.

Metals can bind to proteins to fulfil important biological functions. Predicting the features of mutated binding sites can thus help us understand the connection between specific mutations and their role in diseases.

Identifying abnormalities in medical images across different viewing angles and body parts is a time-consuming task. Deep learning techniques hold great promise for supporting radiologists and improving patient triage decisions. A new study tests the viability of such approaches in resource-limited settings, exploring the effect of pretraining, dataset size and choice of deep learning model in the task of abnormality detection in lower-limb radiographs.

Drug combinations are often an effective means of managing complex diseases, but understanding the synergies of drug combinations requires extensive resources. The authors developed an efficient machine learning model that requires only a limited set of pairwise dose–response measurements for the accurate prediction of synergistic and antagonistic drug combinations.

To better extract meaning from natural language, some less informative words can be removed before a model is trained, which is usually done by using manually curated lists of stopwords. A new information theoretic approach can identify uninformative words automatically and more accurately.

Algorithms and bots are capable of performing some behaviours at human or super-human levels. Humans, however, tend to trust algorithms less than they trust other humans. The authors find that bots do better than humans at inducing cooperation in certain human–machine interactions, but only if the bots do not disclose their true nature as artificial.

Human face recognition is robust to changes in viewpoint, illumination, facial expression and appearance. The authors investigated face recognition in deep convolutional neural networks by manipulating the strength of identity information in a face by caricaturing. They found that networks create a highly organized face similarity structure in which identities and images coexist.

Photonic computing devices have been proposed as a high-speed and energy-efficient approach to implementing neural networks. Using off-the-shelf components, Antonik et al. demonstrate a reservoir computer that recognizes different forms of human action from video streams using photonic neural networks.

Deep learning is currently transforming digital pathology, helping to make more reliable and faster clinical diagnoses. A promising application is in the recognition of malignant white blood cells—an essential step for detecting acute myeloid leukaemia that is challenging even for trained human examiners. An annotated image dataset of over 18,000 white blood cells is compiled and used to train a convolutional neural network for leukocyte classification. The network classifies the most important cell types with high accuracy and can answer clinically relevant binary questions with human-level performance.

Deep neural networks can be led to misclassify an image when minute changes that are imperceptible to humans are introduced. While for some networks this ability can cast doubt on the reliability of the model, it also offers explainability for networks that use more robust regularization.