Born to learn: The inspiration, progress, and future of evolved plastic artificial neural networks

Artificial Neural Network Modeling of Mechanical Properties of 3D-Printed Polyamide 12 and Its Fiber-Reinforced Composites

Fused filament fabrication (FFF) has recently emerged as a sustainable digital manufacturing technology to fabricate polymer composite parts with complex structures and minimal waste. However, FFF-printed composite parts frequently exhibit heterogeneous structures with low mechanical properties. To manufacture high-end parts with good mechanical properties, advanced predictive tools are required. In this paper, Artificial Neural Network (ANN) models were developed to evaluate the mechanical properties of 3D-printed polyamide 12 (PA) and carbon fiber (CF) and glass fiber (GF) reinforced PA composites. Tensile samples were fabricated by FFF, considering two input parameters, such as printing orientation and infill density, and tested to determine the mechanical properties. Then, single- and multi-target ANN models were trained using the forward propagation Levenberg-Marquardt algorithm. Post-training performance analysis indicated that the ANN models work efficiently and accurately in predicting Young's modulus and tensile strength of the 3D-printed PA and fiber-reinforced PA composites, with most relative errors being far less than 5%. In terms of mechanical properties, such as Young's modulus and tensile strength, the 3D-printed composites outperform the unreinforced PA. Printing PA composites with 0° orientation and 100% infill density results in a maximum increase in Young's modulus (up to 98% for CF/PA and 32% for GF/PA) and tensile strength (up to 36% for CF/PA and 18% for GF/PA) compared to the unreinforced PA. This study underscores the potential of the ANN models to predict the mechanical properties of 3D-printed parts, enhancing the use of 3D-printed PA composite components in structural applications.

Automating Speech Audiometry in Quiet and in Noise Using a Deep Neural Network

In addition to pure-tone audiometry tests and electrophysiological tests, a comprehensive hearing evaluation includes assessing a subject's ability to understand speech in quiet and in noise. In fact, speech audiometry tests are commonly used in clinical practice; however, they are time-consuming as they require manual scoring by a hearing professional. To address this issue, we developed an automated speech recognition (ASR) system for scoring subject responses at the phonetic level. The ASR was built using a deep neural network and trained with pre-recorded French speech materials: Lafon's cochlear lists and Dodelé logatoms. Next, we tested the performance and reliability of the ASR in clinical settings with both normal-hearing and hearing-impaired listeners. Our findings indicate that the ASR's performance is statistically similar to manual scoring by expert hearing professionals, both in quiet and in noisy conditions. Moreover, the test-retest reliability of the automated scoring closely matches that of manual scoring. Together, our results validate the use of this deep neural network in both clinical and research contexts for conducting speech audiometry tests in quiet and in noise.

VLAD: Task-agnostic VAE-based lifelong anomaly detection

Lifelong learning represents an emerging machine learning paradigm that aims at designing new methods providing accurate analyses in complex and dynamic real-world environments. Although a significant amount of research has been conducted in image classification and reinforcement learning, very limited work has been done to solve lifelong anomaly detection problems. In this context, a successful method has to detect anomalies while adapting to changing environments and preserving knowledge to avoid catastrophic forgetting. While state-of-the-art online anomaly detection methods are able to detect anomalies and adapt to a changing environment, they are not designed to preserve past knowledge. On the other hand, while lifelong learning methods are focused on adapting to changing environments and preserving knowledge, they are not tailored for detecting anomalies, and often require task labels or task boundaries which are not available in task-agnostic lifelong anomaly detection scenarios. This paper proposes VLAD, a novel VAE-based Lifelong Anomaly Detection method addressing all these challenges simultaneously in complex task-agnostic scenarios. VLAD leverages the combination of lifelong change point detection and an effective model update strategy supported by experience replay with a hierarchical memory maintained by means of consolidation and summarization. An extensive quantitative evaluation showcases the merit of the proposed method in a variety of applied settings. VLAD outperforms state-of-the-art methods for anomaly detection, presenting increased robustness and performance in complex lifelong settings.

Epigenetic opportunities for evolutionary computation

Evolutionary computation is a group of biologically inspired algorithms used to solve complex optimization problems. It can be split into evolutionary algorithms, which take inspiration from genetic inheritance, and swarm intelligence algorithms, that take inspiration from cultural inheritance. However, much of the modern evolutionary literature remains relatively unexplored. To understand which evolutionary mechanisms have been considered, and which have been overlooked, this paper breaks down successful bioinspired algorithms under a contemporary biological framework based on the extended evolutionary synthesis, an extension of the classical, genetics focused, modern synthesis. Although the idea of the extended evolutionary synthesis has not been fully accepted in evolutionary theory, it presents many interesting concepts that could provide benefits to evolutionary computation. The analysis shows that Darwinism and the modern synthesis have been incorporated into evolutionary computation but the extended evolutionary synthesis has been broadly ignored beyond: cultural inheritance, incorporated in the sub-set of swarm intelligence algorithms, evolvability, through covariance matrix adaptation evolution strategy (CMA-ES), and multilevel selection, through multilevel selection genetic algorithm (MLSGA). The framework shows a gap in epigenetic inheritance for evolutionary computation, despite being a key building block in modern interpretations of evolution. This leaves a diverse range of biologically inspired mechanisms as low hanging fruit that should be explored further within evolutionary computation and illustrates the potential of epigenetic based approaches through the recent benchmarks in the literature.

Meta-Learning in Neural Networks: A Survey

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratch using a fixed learning algorithm, meta-learning aims to improve the learning algorithm itself, given the experience of multiple learning episodes. This paradigm provides an opportunity to tackle many conventional challenges of deep learning, including data and computation bottlenecks, as well as generalization. This survey describes the contemporary meta-learning landscape. We first discuss definitions of meta-learning and position it with respect to related fields, such as transfer learning and hyperparameter optimization. We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods today. We survey promising applications and successes of meta-learning such as few-shot learning and reinforcement learning. Finally, we discuss outstanding challenges and promising areas for future research.

Reinforcement Learning for Central Pattern Generation in Dynamical Recurrent Neural Networks

Lifetime learning, or the change (or acquisition) of behaviors during a lifetime, based on experience, is a hallmark of living organisms. Multiple mechanisms may be involved, but biological neural circuits have repeatedly demonstrated a vital role in the learning process. These neural circuits are recurrent, dynamic, and non-linear and models of neural circuits employed in neuroscience and neuroethology tend to involve, accordingly, continuous-time, non-linear, and recurrently interconnected components. Currently, the main approach for finding configurations of dynamical recurrent neural networks that demonstrate behaviors of interest is using stochastic search techniques, such as evolutionary algorithms. In an evolutionary algorithm, these dynamic recurrent neural networks are evolved to perform the behavior over multiple generations, through selection, inheritance, and mutation, across a population of solutions. Although, these systems can be evolved to exhibit lifetime learning behavior, there are no explicit rules built into these dynamic recurrent neural networks that facilitate learning during their lifetime (e.g., reward signals). In this work, we examine a biologically plausible lifetime learning mechanism for dynamical recurrent neural networks. We focus on a recently proposed reinforcement learning mechanism inspired by neuromodulatory reward signals and ongoing fluctuations in synaptic strengths. Specifically, we extend one of the best-studied and most-commonly used dynamic recurrent neural networks to incorporate the reinforcement learning mechanism. First, we demonstrate that this extended dynamical system (model and learning mechanism) can autonomously learn to perform a central pattern generation task. Second, we compare the robustness and efficiency of the reinforcement learning rules in relation to two baseline models, a random walk and a hill-climbing walk through parameter space. Third, we systematically study the effect of the different meta-parameters of the learning mechanism on the behavioral learning performance. Finally, we report on preliminary results exploring the generality and scalability of this learning mechanism for dynamical neural networks as well as directions for future work.

The Imitation Game in Children With Tourette Syndrome: A Lack of Impulse Control to Mirror Environmental Stimuli

The learning process in humans requires continuous contacts with environmental stimuli, especially during neurodevelopmental growth. These functions are assisted by the coding potential of mirror neurons to serve social interactions. This ability to learn imitating the observed behavior is no longer necessary during adulthood, and control mechanisms prevent automatic mirroring. However, children with Gilles de la Tourette syndrome could encounter coding errors at the level of the mirror neurons system as these cortical regions are themselves the ones affected in the syndrome. Combined with impulsivity, the resulting sign would be a manifest echopraxia that persists throughout adulthood, averting these individuals from the appraisal of a spot-on motor control.

Evolving interpretable plasticity for spiking networks

Continuous adaptation allows survival in an ever-changing world. Adjustments in the synaptic coupling strength between neurons are essential for this capability, setting us apart from simpler, hard-wired organisms. How these changes can be mathematically described at the phenomenological level, as so-called ‘plasticity rules’, is essential both for understanding biological information processing and for developing cognitively performant artificial systems. We suggest an automated approach for discovering biophysically plausible plasticity rules based on the definition of task families, associated performance measures and biophysical constraints. By evolving compact symbolic expressions, we ensure the discovered plasticity rules are amenable to intuitive understanding, fundamental for successful communication and human-guided generalization. We successfully apply our approach to typical learning scenarios and discover previously unknown mechanisms for learning efficiently from rewards, recover efficient gradient-descent methods for learning from target signals, and uncover various functionally equivalent STDP-like rules with tuned homeostatic mechanisms.

Our brains are incredibly adaptive. Every day we form memories, acquire new knowledge or refine existing skills. This stands in contrast to our current computers, which typically can only perform pre-programmed actions. Our own ability to adapt is the result of a process called synaptic plasticity, in which the strength of the connections between neurons can change. To better understand brain function and build adaptive machines, researchers in neuroscience and artificial intelligence (AI) are modeling the underlying mechanisms.

So far, most work towards this goal was guided by human intuition – that is, by the strategies scientists think are most likely to succeed. Despite the tremendous progress, this approach has two drawbacks. First, human time is limited and expensive. And second, researchers have a natural – and reasonable – tendency to incrementally improve upon existing models, rather than starting from scratch.

Jordan, Schmidt et al. have now developed a new approach based on ‘evolutionary algorithms’. These computer programs search for solutions to problems by mimicking the process of biological evolution, such as the concept of survival of the fittest. The approach exploits the increasing availability of cheap but powerful computers. Compared to its predecessors (or indeed human brains), it also uses search strategies that are less biased by previous models.

The evolutionary algorithms were presented with three typical learning scenarios. In the first, the computer had to spot a repeating pattern in a continuous stream of input without receiving feedback on how well it was doing. In the second scenario, the computer received virtual rewards whenever it behaved in the desired manner – an example of reinforcement learning. Finally, in the third ‘supervised learning’ scenario, the computer was told exactly how much its behavior deviated from the desired behavior. For each of these scenarios, the evolutionary algorithms were able to discover mechanisms of synaptic plasticity to solve the new task successfully.

Using evolutionary algorithms to study how computers ‘learn’ will provide new insights into how brains function in health and disease. It could also pave the way for developing intelligent machines that can better adapt to the needs of their users.

Real-World Robot Evolution: Why Would it (not) Work?

This paper takes a critical look at the concept of real-world robot evolution discussing specific challenges for making it practicable. After a brief review of the state of the art several enablers are discussed in detail. It is noted that sample efficient evolution is one of the key prerequisites and there are various promising directions towards this in different stages of maturity, including learning as part of the evolutionary system, genotype filtering, and hybridizing real-world evolution with simulations in a new way. Furthermore, it is emphasized that an evolutionary system that works in the real world needs robots that work in the real world. Obvious as it may seem, to achieve this significant complexification of the robots and their tasks is needed compared to the current practice. Finally, the importance of not only building but also understanding evolving robot systems is emphasised, stating that in order to have the technology work we also need the science behind it.

Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle

The plastic modifications in synaptic connectivity is primarily from changes triggered by neuromodulated dopamine signals. These activities are controlled by neuromodulation, which is itself under the control of the brain. The subjective brain’s self-modifying abilities play an essential role in learning and adaptation. The artificial neural networks with neuromodulated plasticity are used to implement transfer learning in the image classification domain. In particular, this has application in image detection, image segmentation, and transfer of learning parameters with significant results. This paper proposes a novel approach to enhance transfer learning accuracy in a heterogeneous source and target, using the neuromodulation of the Hebbian learning principle, called NDHTL (Neuromodulated Dopamine Hebbian Transfer Learning). Neuromodulation of plasticity offers a powerful new technique with applications in training neural networks implementing asymmetric backpropagation using Hebbian principles in transfer learning motivated CNNs (Convolutional neural networks). Biologically motivated concomitant learning, where connected brain cells activate positively, enhances the synaptic connection strength between the network neurons. Using the NDHTL algorithm, the percentage of change of the plasticity between the neurons of the CNN layer is directly managed by the dopamine signal’s value. The discriminative nature of transfer learning fits well with the technique. The learned model’s connection weights must adapt to unseen target datasets with the least cost and effort in transfer learning. Using distinctive learning principles such as dopamine Hebbian learning in transfer learning for asymmetric gradient weights update is a novel approach. The paper emphasizes the NDHTL algorithmic technique as synaptic plasticity controlled by dopamine signals in transfer learning to classify images using source-target datasets. The standard transfer learning using gradient backpropagation is a symmetric framework. Experimental results using CIFAR-10 and CIFAR-100 datasets show that the proposed NDHTL algorithm can enhance transfer learning efficiency compared to existing methods.

Reinforcement learning for robot research: A comprehensive review and open issues

Applying the learning mechanism of natural living beings to endow intelligent robots with humanoid perception and decision-making wisdom becomes an important force to promote the revolution of science and technology in robot domains. Advances in reinforcement learning (RL) over the past decades have led robotics to be highly automated and intelligent, which ensures safety operation instead of manual work and implementation of more intelligence for many challenging tasks. As an important branch of machine learning, RL can realize sequential decision-making under uncertainties through end-to-end learning and has made a series of significant breakthroughs in robot applications. In this review article, we cover RL algorithms from theoretical background to advanced learning policies in different domains, which accelerate to solving practical problems in robotics. The challenges, open issues, and our thoughts on future research directions of RL are also presented to discover new research areas with the objective to motivate new interest.

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.

Evolving the Behavior of Machines: From Micro to Macroevolution

Evolution gave rise to creatures that are arguably more sophisticated than the greatest human-designed systems. This feat has inspired computer scientists since the advent of computing and led to optimization tools that can evolve complex neural networks for machines-an approach known as "neuroevolution." After a few successes in designing evolvable representations for high-dimensional artifacts, the field has been recently revitalized by going beyond optimization: to many, the wonder of evolution is less in the perfect optimization of each species than in the creativity of such a simple iterative process, that is, in the diversity of species. This modern view of artificial evolution is moving the field away from microevolution, following a fitness gradient in a niche, to macroevolution, filling many niches with highly different species. It already opened promising applications, like evolving gait repertoires, video game levels for different tastes, and diverse designs for aerodynamic bikes.

A Curiosity-Based Learning Method for Spiking Neural Networks

Spiking Neural Networks (SNNs) have shown favorable performance recently. Nonetheless, the time-consuming computation on neuron level and complex optimization limit their real-time application. Curiosity has shown great performance in brain learning, which helps biological brains grasp new knowledge efficiently and actively. Inspired by this leaning mechanism, we propose a curiosity-based SNN (CBSNN) model, which contains four main learning processes. Firstly, the network is trained with biologically plausible plasticity principles to get the novelty estimations of all samples in only one epoch; secondly, the CBSNN begins to repeatedly learn the samples whose novelty estimations exceed the novelty threshold and dynamically update the novelty estimations of samples according to the learning results in five epochs; thirdly, in order to avoid the overfitting of the novel samples and forgetting of the learned samples, CBSNN retrains all samples in one epoch; finally, step two and step three are periodically taken until network convergence. Compared with the state-of-the-art Voltage-driven Plasticity-centric SNN (VPSNN) under standard architecture, our model achieves a higher accuracy of 98.55% with only 54.95% of its computation cost on the MNIST hand-written digit recognition dataset. Similar conclusion can also be found out in other datasets, i.e., Iris, NETtalk, Fashion-MNIST, and CIFAR-10, respectively. More experiments and analysis further prove that such curiosity-based learning theory is helpful in improving the efficiency of SNNs. As far as we know, this is the first practical combination of the curiosity mechanism and SNN, and these improvements will make the realistic application of SNNs possible on more specific tasks within the von Neumann framework.

Evolving the pulmonary nodules diagnosis from classical approaches to deep learning-aided decision support: three decades' development course and future prospect

PURPOSE

Lung cancer is the commonest cause of cancer deaths worldwide, and its mortality can be reduced significantly by performing early diagnosis and screening. Since the 1960s, driven by the pressing needs to accurately and effectively interpret the massive volume of chest images generated daily, computer-assisted diagnosis of pulmonary nodule has opened up new opportunities to relax the limitation from physicians' subjectivity, experiences and fatigue. And the fair access to the reliable and affordable computer-assisted diagnosis will fight the inequalities in incidence and mortality between populations. It has been witnessed that significant and remarkable advances have been achieved since the 1980s, and consistent endeavors have been exerted to deal with the grand challenges on how to accurately detect the pulmonary nodules with high sensitivity at low false-positive rate as well as on how to precisely differentiate between benign and malignant nodules. There is a lack of comprehensive examination of the techniques' development which is evolving the pulmonary nodules diagnosis from classical approaches to machine learning-assisted decision support. The main goal of this investigation is to provide a comprehensive state-of-the-art review of the computer-assisted nodules detection and benign-malignant classification techniques developed over three decades, which have evolved from the complicated ad hoc analysis pipeline of conventional approaches to the simplified seamlessly integrated deep learning techniques. This review also identifies challenges and highlights opportunities for future work in learning models, learning algorithms and enhancement schemes for bridging current state to future prospect and satisfying future demand.

CONCLUSION

It is the first literature review of the past 30 years' development in computer-assisted diagnosis of lung nodules. The challenges indentified and the research opportunities highlighted in this survey are significant for bridging current state to future prospect and satisfying future demand. The values of multifaceted driving forces and multidisciplinary researches are acknowledged that will make the computer-assisted diagnosis of pulmonary nodules enter into the main stream of clinical medicine and raise the state-of-the-art clinical applications as well as increase both welfares of physicians and patients. We firmly hold the vision that fair access to the reliable, faithful, and affordable computer-assisted diagnosis for early cancer diagnosis would fight the inequalities in incidence and mortality between populations, and save more lives.

Expectation Learning for Stimulus Prediction Across Modalities Improves Unisensory Classification

Expectation learning is a unsupervised learning process which uses multisensory bindings to enhance unisensory perception. For instance, as humans, we learn to associate a barking sound with the visual appearance of a dog, and we continuously fine-tune this association over time, as we learn, e.g., to associate high-pitched barking with small dogs. In this work, we address the problem of developing a computational model that addresses important properties of expectation learning, in particular focusing on the lack of explicit external supervision other than temporal co-occurrence. To this end, we present a novel hybrid neural model based on audio-visual autoencoders and a recurrent self-organizing network for multisensory bindings that facilitate stimulus reconstructions across different sensory modalities. We refer to this mechanism as stimulus prediction across modalities and demonstrate that the proposed model is capable of learning concept bindings by evaluating it on unisensory classification tasks for audio-visual stimuli using the 43,500 Youtube videos from the animal subset of the AudioSet corpus.