Multidimensional cerebellar computations for flexible kinematic control of movements

Both the environment and our body keep changing dynamically. Hence, ensuring movement precision requires adaptation to multiple demands occurring simultaneously. Here we show that the cerebellum performs the necessary multi-dimensional computations for the flexible control of different movement parameters depending on the prevailing context. This conclusion is based on the identification of a manifold-like activity in both mossy fibers (MF, network input) and Purkinje cells (PC, output), recorded from monkeys performing a saccade task. Unlike MFs, the properties of PC manifolds developed selective representations of individual movement parameters. Error feedback-driven climbing fiber input modulated the PC manifolds to predict specific, error type-dependent changes in subsequent actions. Furthermore, a feed-forward network model that simulated MF-to-PC transformations revealed that amplification and restructuring of the lesser variability in the MF activity is a pivotal circuit mechanism. Therefore, flexible control of movement by the cerebellum crucially depends on its capacity for multi-dimensional computations.

An approach framework of transfer learning, adversarial training and hierarchical multi-task learning - a case study of disinformation detection with offensive text

With society going online and disinformation getting accepted as a phenomena that we have to live with, there is a growing need to automatically detect offensive text on modern social media platforms. But the lack of enough balanced labeled data, constantly evolving socio-linguistic patterns and ever-changing definition of offensive text make it a challenging task. This is a common pattern witnessed in all disinformation detection tasks such as detection of propaganda, rumour, fake news, hate etc. The work described in this paper improves upon the existing body of techniques by bringing in an approach framework that can surpass the existing benchmarks. Firstly, it addresses the imbalanced and insufficient nature of available labeled dataset. Secondly, learning using relates tasks through multi-task learning has been proved to be an effective approach in this domain but it has the unrealistic requirement of labeled data for all related tasks. The framework presented here suitably uses transfer learning in lieu of multi-task learning to address this issue. Thirdly, it builds a model explicitly addressing the hierarchical nature in the taxonomy of disinformation being detected as that delivers a stronger error feedback to the learning tasks. Finally, the model is made more robust by adversarial training. The work presented in this paper uses offensive text detection as a case study and shows convincing results for the chosen approach. The framework adopted can be easily replicated in other similar learning tasks facing a similar set of challenges.

Error feedback regulation for 1D anti-stable wave equation

This paper is concerned with the boundary error feedback regulation for a one-dimensional anti-stable wave equation with distributed disturbance generated by a finite-dimensional exogenous system. Transport equation and regulator equation are introduced first to deal with the anti-damping on boundary and the distributed disturbance of the original system. Then, the tracking error and its derivative are measured to design an observer for both exosystem and auxiliary partial differential equation (PDE) system to recover the state. After proving the well-posedness of the regulator equations, we propose an observer-based controller to regulate the tracking error to zero exponentially and keep the states of all the internal loop uniformly bounded. Finally, some numerical simulations are presented to validate the effectiveness of the proposed controller.

Frequency Regulation System: A Deep Learning Identification, Type-3 Fuzzy Control and LMI Stability Analysis

In this paper, the problem of frequency regulation in the multi-area power systems with demand response, energy storage system (ESS) and renewable energy generators is studied. Dissimilarly to most studies in this field, the dynamics of all units in all areas are considered to be unknown. Furthermore time-varying solar radiation, wind speed dynamics, multiple load changes, demand response (DR), and ESS are considered. A novel dynamic fractional-order model based on restricted Boltzmann machine (RBM) and deep learning contrastive divergence (CD) algorithm is presented for online identification. The controller is designed by the dynamic estimated model, error feedback controller and interval type-3 fuzzy logic compensator (IT3-FLC). The gains of error feedback controller and tuning rules of the estimated dynamic model are extracted through the fractional-order stability analysis by the linear matrix inequality (LMI) approach. The superiority of a schemed controller in contrast to the type-1 and type-2 FLCs is demonstrated in various conditions, such as time-varying wind speed, solar radiation, multiple load changes, and perturbed dynamics.

The Associative Learning Prediction Error Feedback Loop as Reversible Driving Belt of the Bioenergetics of Longevity

Leukocyte telomere shortening is a useful biomarker of biological and cellular age that occurs at an accelerated rate in anxiety disorders and posttraumatic stress disorder (PTSD). Intriguingly, inhibitory learning — the systematic exposure to noxious stimuli that serves as a basis for many treatments for anxiety, phobia, and PTSD —reduces relative telomeres attrition rates and increases protective telomerase activity in a manner predictive of treatment response. How does inhibitory learning, a behavioral strategy, modulate organismal chromosomal activity? Inhibitory learning may induce repeated mismatch between treatment expectations, intrasession states, and eventual outcome. Nevertheless, inhibitory learning can incentivize repetition of the behavior. Thus, this paper aims to conceptualize inhibitory learning as involving a ‘prediction error feedback loop’, i.e., a series of self-perpetuating prediction errors — mismatches between expectations and outcomes — that enhances neural inhibitory regulation to effectuate extinction. Inhibitory learning is necessarily predicated upon an opposing process – excitatory learning – that may be conceptualized as a prediction error feedback loop that operates in reverse to inhibitory learning and enhances neural excitability as arousal. Together, excitatory and inhibitory learning may be elements of an associative learning prediction error feedback loop responsible for modulating neural bioenergetic rates, leading to changes in downstream cellular signaling that could explain reduced or increased rates of leukocyte telomere shortening and telomerase activity from each behavioral strategy, respectively.

Design and Application of Model Based on Bayesian Network

At present, Bayesian networks lack consistent algorithms that support structure establishment, parameter learning, and knowledge reasoning, making it impossible to connect knowledge establishment and application processes. In view of this situation, by designing a genetic algorithm coding method suitable for Bayesian network learning, crossover and mutation operators with adjustment strategies, the fitness function for reasoning error feedback can be carried out. Experimental results show that the new algorithm not only simultaneously optimizes the network structure and parameters, but also can adaptively learn and correct inference errors, and has a more satisfactory knowledge inference accuracy rate.

Quantized Adam with Error Feedback

In this article, we present a distributed variant of an adaptive stochastic gradient method for training deep neural networks in the parameter-server model. To reduce the communication cost among the workers and server, we incorporate two types of quantization schemes, i.e., gradient quantization and weight quantization, into the proposed distributed Adam. In addition, to reduce the bias introduced by quantization operations, we propose an error-feedback technique to compensate for the quantized gradient. Theoretically, in the stochastic nonconvex setting, we show that the distributed adaptive gradient method with gradient quantization and error feedback converges to the first-order stationary point, and that the distributed adaptive gradient method with weight quantization and error feedback converges to the point related to the quantized level under both the single-worker and multi-worker modes. Last, we apply the proposed distributed adaptive gradient methods to train deep neural networks. Experimental results demonstrate the efficacy of our methods.