Constructing optimized binary masks for reservoir computing with delay systems.
Ontology highlight
ABSTRACT:
SUBMITTER: Appeltant L
PROVIDER: S-EPMC3887384 | biostudies-other | 2014
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Delays are ubiquitous in biological systems, ranging from genetic regulatory networks and synaptic conductances, to predator/pray population interactions. The evidence is mounting, not only to the presence of delays as physical constraints in signal propagation speed, but also to their functional role in providing dynamical diversity to the systems that comprise them. The latter observation in biological systems inspired the recent development of a computational architecture that harnesses this dynamical diversity, by delay-coupling a single nonlinear element to itself. This architecture is a particular realization of Reservoir Computing, where stimuli are injected into the system in time rather than in space as is the case with classical recurrent neural network realizations. This architecture also exhibits an internal memory which fades in time, an important prerequisite to the functioning of any reservoir computing device. However, fading memory is also a limitation to any computation that requires persistent storage. In order to overcome this limitation, the current work introduces an extended version to the single node Delay-Coupled Reservoir, that is based on trained linear feedback. We show by numerical simulations that adding task-specific linear feedback to the single node Delay-Coupled Reservoir extends the class of solvable tasks to those that require nonfading memory. We demonstrate, through several case studies, the ability of the extended system to carry out complex nonlinear computations that depend on past information, whereas the computational power of the system with fading memory alone quickly deteriorates. Our findings provide the theoretical basis for future physical realizations of a biologically-inspired ultrafast computing device with extended functionality.
| S-EPMC5081200 | biostudies-literature
Project description:The reservoir computing (RC) is increasingly used to learn the synchronization behavior of chaotic systems as well as the dynamical behavior of complex systems, but it is scarcely applied in studying synchronization of non-smooth chaotic systems likely due to its complexity leading to the unimpressive effect. Here proposes a simulated annealing-based differential evolution (SADE) algorithm for the optimal parameter selection in the reservoir, and constructs an improved RC model for synchronization, which can work well not only for non-smooth chaotic systems but for smooth ones. Extensive simulations show that the trained RC model with optimal parameters has far longer prediction time than those with empirical and random parameters. More importantly, the well-trained RC system can be well synchronized to its original chaotic system as well as its replicate RC system via one shared signal, whereas the traditional RC system with empirical or random parameters fails for some chaotic systems, particularly for some non-smooth chaotic systems.
| S-EPMC10761703 | biostudies-literature
Project description:Photonic implementations of reservoir computing (RC) promise to reach ultra-high bandwidth of operation with moderate training efforts. Several optoelectronic demonstrations reported state of the art performances for hard tasks as speech recognition, object classification and time series prediction. Scaling these systems in space and time faces challenges in control complexity, size and power demand, which can be relieved by integrated optical solutions. Silicon photonics can be the disruptive technology to achieve this goal. However, the experimental demonstrations have been so far focused on spatially distributed reservoirs, where the massive use of splitters/combiners and the interconnection loss limits the number of nodes. Here, we propose and validate an all optical RC scheme based on a silicon microring (MR) and time multiplexing. The input layer is encoded in the intensity of a pump beam, which is nonlinearly transferred to the free carrier concentration in the MR and imprinted on a secondary probe. We harness the free carrier dynamics to create a chain-like reservoir topology with 50 virtual nodes. We give proof of concept demonstrations of RC by solving two nontrivial tasks: the delayed XOR and the classification of Iris flowers. This forms the basic building block from which larger hybrid spatio-temporal reservoirs with thousands of nodes can be realized with a limited set of resources.
| S-EPMC8329232 | biostudies-literature
Project description:Reservoir computing is a recently introduced, highly efficient bio-inspired approach for processing time dependent data. The basic scheme of reservoir computing consists of a non linear recurrent dynamical system coupled to a single input layer and a single output layer. Within these constraints many implementations are possible. Here we report an optoelectronic implementation of reservoir computing based on a recently proposed architecture consisting of a single non linear node and a delay line. Our implementation is sufficiently fast for real time information processing. We illustrate its performance on tasks of practical importance such as nonlinear channel equalization and speech recognition, and obtain results comparable to state of the art digital implementations.
| S-EPMC3286854 | biostudies-literature
Project description:Reservoir computing is a best-in-class machine learning algorithm for processing information generated by dynamical systems using observed time-series data. Importantly, it requires very small training data sets, uses linear optimization, and thus requires minimal computing resources. However, the algorithm uses randomly sampled matrices to define the underlying recurrent neural network and has a multitude of metaparameters that must be optimized. Recent results demonstrate the equivalence of reservoir computing to nonlinear vector autoregression, which requires no random matrices, fewer metaparameters, and provides interpretable results. Here, we demonstrate that nonlinear vector autoregression excels at reservoir computing benchmark tasks and requires even shorter training data sets and training time, heralding the next generation of reservoir computing.
| S-EPMC8455577 | biostudies-literature
Project description:The connectivity of Artificial Neural Networks (ANNs) is different from the one observed in Biological Neural Networks (BNNs). Can the wiring of actual brains help improve ANNs architectures? Can we learn from ANNs about what network features support computation in the brain when solving a task? At a meso/macro-scale level of the connectivity, ANNs' architectures are carefully engineered and such those design decisions have crucial importance in many recent performance improvements. On the other hand, BNNs exhibit complex emergent connectivity patterns at all scales. At the individual level, BNNs connectivity results from brain development and plasticity processes, while at the species level, adaptive reconfigurations during evolution also play a major role shaping connectivity. Ubiquitous features of brain connectivity have been identified in recent years, but their role in the brain's ability to perform concrete computations remains poorly understood. Computational neuroscience studies reveal the influence of specific brain connectivity features only on abstract dynamical properties, although the implications of real brain networks topologies on machine learning or cognitive tasks have been barely explored. Here we present a cross-species study with a hybrid approach integrating real brain connectomes and Bio-Echo State Networks, which we use to solve concrete memory tasks, allowing us to probe the potential computational implications of real brain connectivity patterns on task solving. We find results consistent across species and tasks, showing that biologically inspired networks perform as well as classical echo state networks, provided a minimum level of randomness and diversity of connections is allowed. We also present a framework, bio2art, to map and scale up real connectomes that can be integrated into recurrent ANNs. This approach also allows us to show the crucial importance of the diversity of interareal connectivity patterns, stressing the importance of stochastic processes determining neural networks connectivity in general.
| S-EPMC9710781 | biostudies-literature
Project description:Reservoir computing (RC) offers efficient temporal information processing with low training cost. All-ferroelectric implementation of RC is appealing because it can fully exploit the merits of ferroelectric memristors (e.g., good controllability); however, this has been undemonstrated due to the challenge of developing ferroelectric memristors with distinctly different switching characteristics specific to the reservoir and readout network. Here, we experimentally demonstrate an all-ferroelectric RC system whose reservoir and readout network are implemented with volatile and nonvolatile ferroelectric diodes (FDs), respectively. The volatile and nonvolatile FDs are derived from the same Pt/BiFeO3/SrRuO3 structure via the manipulation of an imprint field (Eimp). It is shown that the volatile FD with Eimp exhibits short-term memory and nonlinearity while the nonvolatile FD with negligible Eimp displays long-term potentiation/depression, fulfilling the functional requirements of the reservoir and readout network, respectively. Hence, the all-ferroelectric RC system is competent for handling various temporal tasks. In particular, it achieves an ultralow normalized root mean square error of 0.017 in the Hénon map time-series prediction. Besides, both the volatile and nonvolatile FDs demonstrate long-term stability in ambient air, high endurance, and low power consumption, promising the all-ferroelectric RC system as a reliable and low-power neuromorphic hardware for temporal information processing.
| S-EPMC10275999 | biostudies-literature
Project description:Reservoir computing is a brain-inspired machine learning framework that employs a signal-driven dynamical system, in particular harnessing common-signal-induced synchronization which is a widely observed nonlinear phenomenon. Basic understanding of a working principle in reservoir computing can be expected to shed light on how information is stored and processed in nonlinear dynamical systems, potentially leading to progress in a broad range of nonlinear sciences. As a first step toward this goal, from the viewpoint of nonlinear physics and information theory, we study the memory-nonlinearity trade-off uncovered by Dambre et al. (2012). Focusing on a variational equation, we clarify a dynamical mechanism behind the trade-off, which illustrates why nonlinear dynamics degrades memory stored in dynamical system in general. Moreover, based on the trade-off, we propose a mixture reservoir endowed with both linear and nonlinear dynamics and show that it improves the performance of information processing. Interestingly, for some tasks, significant improvements are observed by adding a few linear dynamics to the nonlinear dynamical system. By employing the echo state network model, the effect of the mixture reservoir is numerically verified for a simple function approximation task and for more complex tasks.
| S-EPMC5579006 | biostudies-literature
Project description:Reservoir computing, a new method of machine learning, has recently been used to predict the state evolution of various chaotic dynamic systems. It has significant advantages in terms of training cost and adjusted parameters; however, the prediction length is limited. For classic reservoir computing, the prediction length can only reach five to six Lyapunov times. Here, we modified the method of reservoir computing by adding feedback, continuous or discrete, to "calibrate" the input of the reservoir and then reconstruct the entire dynamic systems. The reconstruction length appreciably increased and the training length obviously decreased. The reconstructing of dynamical systems is studied in detail under this method. The reconstruction can be significantly improved both in length and accuracy. Additionally, we summarized the effect of different kinds of input feedback. The more it interacts with others in dynamical equations, the better the reconstructions. Nonlinear terms can reveal more information than linear terms once the interaction terms are equal. This method has proven effective via several classical chaotic systems. It can be superior to traditional reservoir computing in reconstruction, provides new hints in computing promotion, and may be used in some real applications.
| S-EPMC9522934 | biostudies-literature
Project description:Chunking is the process by which frequently repeated segments of temporal inputs are concatenated into single units that are easy to process. Such a process is fundamental to time-series analysis in biological and artificial information processing systems. The brain efficiently acquires chunks from various information streams in an unsupervised manner; however, the underlying mechanisms of this process remain elusive. A widely-adopted statistical method for chunking consists of predicting frequently repeated contiguous elements in an input sequence based on unequal transition probabilities over sequence elements. However, recent experimental findings suggest that the brain is unlikely to adopt this method, as human subjects can chunk sequences with uniform transition probabilities. In this study, we propose a novel conceptual framework to overcome this limitation. In this process, neural networks learn to predict dynamical response patterns to sequence input rather than to directly learn transition patterns. Using a mutually supervising pair of reservoir computing modules, we demonstrate how this mechanism works in chunking sequences of letters or visual images with variable regularity and complexity. In addition, we demonstrate that background noise plays a crucial role in correctly learning chunks in this model. In particular, the model can successfully chunk sequences that conventional statistical approaches fail to chunk due to uniform transition probabilities. In addition, the neural responses of the model exhibit an interesting similarity to those of the basal ganglia observed after motor habit formation.
| S-EPMC6193738 | biostudies-literature