Explore the vast range of titles available.

Research on brain–computer interfaces (BCIs) has become more democratic in recent decades, and experiments using electroencephalography (EEG)-based BCIs has dramatically increased. The variety of protocol designs and the growing interest in physiological computing require parallel improvements in processing and classification of both EEG signals and bio signals, such as electrodermal activity (EDA), heart rate (HR) or breathing. If some EEG-based analysis tools are already available for online BCIs with a number of online BCI platforms (e.g., BCI2000 or OpenViBE), it remains crucial to perform offline analyses in order to design, select, tune, validate and test algorithms before using them online. Moreover, studying and comparing those algorithms usually requires expertise in programming, signal processing and machine learning, whereas numerous BCI researchers come from other backgrounds with limited or no training in such skills. Finally, existing BCI toolboxes are focused on EEG and other brain signals but usually do not include processing tools for other bio signals. Therefore, in this paper, we describe BioPyC, a free, open-source and easy-to-use Python platform for offline EEG and biosignal processing and classification. Based on an intuitive and well-guided graphical interface, four main modules allow the user to follow the standard steps of the BCI process without any programming skills: (1) reading different neurophysiological signal data formats, (2) filtering and representing EEG and bio signals, (3) classifying them, and (4) visualizing and performing statistical tests on the results. We illustrate BioPyC use on four studies, namely classifying mental tasks, the cognitive workload, emotions and attention states from EEG signals.

Optimization and decision making problems in various fields of engineering have a major impact in this current era. Processing time and utilizing memory is very high for the currently available data. This is due to its size and the need for scaling from zettabyte to yottabyte. Some problems need to find solutions and there are other types of issues that need to improve their current best solution. Modelling and implementing a new heuristic algorithm may be time consuming but has some strong primary motivation - like a minimal improvement in the solution itself can reduce the computational cost. The solution thus obtained was better. In both these situations, designing heuristics and meta-heuristics algorithm has proved it’s worth. Hyper heuristic solutions will be needed to compute solutions in a much better time and space complexities. It creates a solution by combining heuristics to generate automated search space from which generalized solutions can be tuned out. This paper provides in-depth knowledge on nature-inspired computing models, meta-heuristic models, hybrid meta heuristic models and hyper heuristic model. This work’s major contribution is on building a hyper heuristics approach from a meta-heuristic algorithm for any general problem domain. Various traditional algorithms and new generation meta heuristic algorithms has also been explained for giving readers a better understanding.

This Research Topic provides a platform to highlight the outstanding contributions of emerging talents in the field of neuromorphic engineering. Through this dedicated series, we aim to showcase the promising work of student researchers within Neuromorphic Engineering.

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

In this study, a distributed active noise control (DANC) system for spatial noise control in a network of acoustic sensor nodes based on the behavioural traits of felines is presented. An unified strategy based on incremental co-operative learning and cat swarm intelligence is proposed for noise mitigation in spatial region. The hybrid nature of the proposed incremental cat swarm optimisation (ICSO) algorithm provides efficient noise control without prior estimation of multiple secondary paths. In the developed ICSO-based DANC scheme, the individual sensor nodes communicate the intermediate solutions using incremental mode of cooperation to attain overall global noise mitigation over the distributed network. The performance of the proposed ICSO based DANC scheme is validated for tonal, broadband and practical air conditioner noise control test scenarios. Evaluation results show that the proposed system achieves faster convergence with computational efficiency of over 36% and ∼2–9 dB improvement in noise cancellation for different noise cases and acoustic environments over genetic algorithm and particle swarm optimisation based DANC counterparts.

We propose a developmental model inspired by the cortico-basal system (CX-BG) for vocal learning in babies and for solving the correspondence mismatch problem they face when they hear unfamiliar voices, with different tones and pitches. This model is based on the neural architecture INFERNO standing for Iterative Free-Energy Optimization of Recurrent Neural Networks. Free-energy minimization is used for rapidly exploring, selecting and learning the optimal choices of actions to perform (eg sound production) in order to reproduce and control as accurately as possible the spike trains representing desired perceptions (eg sound categories). We detail in this paper the CX-BG system responsible for linking causally the sound and motor primitives at the order of a few milliseconds. Two experiments performed with a small and a large audio database show the capabilities of exploration, generalization and robustness to noise of our neural architecture in retrieving audio primitives during vocal learning and during acoustic matching with unheared voices (different genders and tones).

Embedding Artificial Intelligence onto low-power devices is a challenging task that has been partly overcome with recent advances in machine learning and hardware design. Presently, deep neural networks can be deployed on embedded targets to perform different tasks such as speech recognition, object detection or Human Activity Recognition. However, there is still room for optimization of deep neural networks onto embedded devices. These optimizations mainly address power consumption, memory and real-time constraints, but also an easier deployment at the edge. Moreover, there is still a need for a better understanding of what can be achieved for different use cases. This work focuses on quantization and deployment of deep neural networks onto low-power 32-bit microcontrollers. The quantization methods, relevant in the context of an embedded execution onto a microcontroller, are first outlined. Then, a new framework for end-to-end deep neural networks training, quantization and deployment is presented. This framework, called MicroAI, is designed as an alternative to existing inference engines (TensorFlow Lite for Microcontrollers and STM32Cube.AI). Our framework can indeed be easily adjusted and/or extended for specific use cases. Execution using single precision 32-bit floating-point as well as fixed-point on 8- and 16 bits integers are supported. The proposed quantization method is evaluated with three different datasets (UCI-HAR, Spoken MNIST and GTSRB). Finally, a comparison study between MicroAI and both existing embedded inference engines is provided in terms of memory and power efficiency. On-device evaluation is done using ARM Cortex-M4F-based microcontrollers (Ambiq Apollo3 and STM32L452RE).

Deep learning (DL) has become an important machine learning approach that has been widely successful in many applications. Currently, DL is one of the best methods of extracting knowledge from large sets of raw data in a (nearly) self-organized manner. The technical design of DL depends on the feed-forward information flow principle of artificial neural networks with multiple layers of hidden neurons, which form deep neural networks (DNNs). DNNs have various architectures and parameters and are often developed for specific applications. However, the training process of DNNs can be prolonged based on the application and training set size (Gong et al. 2015). Moreover, finding the most accurate and efficient architecture of a deep learning system in a reasonable time is a potential difficulty associated with this approach. Swarm intelligence (SI) and evolutionary computing (EC) techniques represent simulation-driven non-convex optimization frameworks with few assumptions based on objective functions. These methods are flexible and have been proven effective in many applications; therefore, they can be used to improve DL by optimizing the applied learning models. This paper presents a comprehensive survey of the most recent approaches involving the hybridization of SI and EC algorithms for DL, the architecture of DNNs, and DNN training to improve the classification accuracy. The paper reviews the significant roles of SI and EC in optimizing the hyper-parameters and architectures of a DL system in context to large scale data analytics. Finally, we identify some open problems for further research, as well as potential issues related to DL that require improvements, and an extensive bibliography of the pertinent research is presented.

In natural behaviour, animals actively interrogate their environments using endogenously generated ‘question-and-answer’ strategies. However, in laboratory settings participants typically engage with externally imposed stimuli and tasks, and the mechanisms of active sampling remain poorly understood. We review a nascent neuroscientific literature that examines active-sampling policies and their relation to attention and curiosity. We distinguish between information sampling, in which organisms reduce uncertainty relevant to a familiar task, and information search, in which they investigate in an open-ended fashion to discover new tasks. We review evidence that both sampling and search depend on individual preferences over cognitive states, including attitudes towards uncertainty, learning progress and types of information. We propose that, although these preferences are non-instrumental and can on occasion interfere with external goals, they are important heuristics that allow organisms to cope with the high complexity of both sampling and search, and generate curiosity-driven investigations in large, open environments in which rewards are sparse and ex ante unknown.

The state-of-the-art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, Nagai et al. (Int J Multimed Inf Retr 7(1):3–16, 2018), Uchida et al. (Embedding watermarks into deep neural networks, ICMR, 2017) proposed to watermark convolutional neural networks for image classification, by embedding information into their weights. While this is a clear progress toward model protection, this technique solely allows for extracting the watermark from a network that one accesses locally and entirely. Instead, we aim at allowing the extraction of the watermark from a neural network (or any other machine learning model) that is operated remotely , and available through a service API. To this end, we propose to mark the model’s action itself, tweaking slightly its decision frontiers so that a set of specific queries convey the desired information. In the present paper, we formally introduce the problem and propose a novel zero-bit watermarking algorithm that makes use of adversarial model examples . While limiting the loss of performance of the protected model, this algorithm allows subsequent extraction of the watermark using only few queries. We experimented the approach on three neural networks designed for image classification, in the context of MNIST digit recognition task.