Powelllam5889

Neural networks with a large number of parameters are prone to overfitting problems when trained on a relatively small training set. Introducing weight penalties of regularization is a promising technique for solving this problem. Taking inspiration from the dynamic plasticity of dendritic spines, which plays an important role in the maintenance of memory, this letter proposes a brain-inspired developmental neural network based on dendritic spine dynamics (BDNN-dsd). The dynamic structure changes of dendritic spines include appearing, enlarging, shrinking, and disappearing. MCC950 purchase Such spine plasticity depends on synaptic activity and can be modulated by experiences-in particular, long-lasting synaptic enhancement/suppression (LTP/LTD), coupled with synapse formation (or enlargement)/elimination (or shrinkage), respectively. Subsequently, spine density characterizes an approximate estimate of the total number of synapses between neurons. Motivated by this, we constrain the weight to a tunable bound that can be adaptively modulated based on synaptic activity. Dynamic weight bound could limit the relatively redundant synapses and facilitate the contributing synapses. Extensive experiments demonstrate the effectiveness of our method on classification tasks of different complexity with the MNIST, Fashion MNIST, and CIFAR-10 data sets. Furthermore, compared to dropout and L2 regularization algorithms, our method can improve the network convergence rate and classification performance even for a compact network.Ordinal regression is aimed at predicting an ordinal class label. In this letter, we consider its semisupervised formulation, in which we have unlabeled data along with ordinal-labeled data to train an ordinal regressor. There are several metrics to evaluate the performance of ordinal regression, such as the mean absolute error, mean zero-one error, and mean squared error. However, the existing studies do not take the evaluation metric into account, restrict model choice, and have no theoretical guarantee. To overcome these problems, we propose a novel generic framework for semisupervised ordinal regression based on the empirical risk minimization principle that is applicable to optimizing all of the metrics mentioned above. In addition, our framework has flexible choices of models, surrogate losses, and optimization algorithms without the common geometric assumption on unlabeled data such as the cluster assumption or manifold assumption. We provide an estimation error bound to show that our risk estimator is consistent. Finally, we conduct experiments to show the usefulness of our framework.Recurrent neural network (RNN) models trained to perform cognitive tasks are a useful computational tool for understanding how cortical circuits execute complex computations. However, these models are often composed of units that interact with one another using continuous signals and overlook parameters intrinsic to spiking neurons. Here, we develop a method to directly train not only synaptic-related variables but also membrane-related parameters of a spiking RNN model. Training our model on a wide range of cognitive tasks resulted in diverse yet task-specific synaptic and membrane parameters. We also show that fast membrane time constants and slow synaptic decay dynamics naturally emerge from our model when it is trained on tasks associated with working memory (WM). Further dissecting the optimized parameters revealed that fast membrane properties are important for encoding stimuli, and slow synaptic dynamics are needed for WM maintenance. This approach offers a unique window into how connectivity patterns and intrinsic neuronal properties contribute to complex dynamics in neural populations.Machine learning is a good tool to simulate human cognitive skills as it is about mapping perceived information to various labels or action choices, aiming at optimal behavior policies for a human or an artificial agent operating in the environment. Regarding autonomous systems, objects and situations are perceived by some receptors as divided between sensors. Reactions to the input (e.g., actions) are distributed among the particular capability providers or actuators. Cognitive models can be trained as, for example, neural networks. We suggest training such models for cases of potential disabilities. link2 Disability can be either the absence of one or more cognitive sensors or actuators at different levels of cognitive model. We adapt several neural network architectures to simulate various cognitive disabilities. The idea has been triggered by the "coolability" (enhanced capability) paradox, according to which a person with some disability can be more efficient in using other capabilities. Therefore, an autonomous system (human or artificial) pretrained with simulated disabilities will be more efficient when acting in adversarial conditions. We consider these coolabilities as complementary artificial intelligence and argue on the usefulness if this concept for various applications.Epilepsy is one of the most common brain disorders worldwide, affecting millions of people every year. Although significant effort has been put into better understanding it and mitigating its effects, the conventional treatments are not fully effective. Advances in computational neuroscience, using mathematical dynamic models that represent brain activities at different scales, have enabled addressing epilepsy from a more theoretical standpoint. In particular, the recently proposed Epileptor model stands out among these models, because it represents well the main features of seizures, and the results from its simulations have been consistent with experimental observations. In addition, there has been an increasing interest in designing control techniques for Epileptor that might lead to possible realistic feedback controllers in the future. However, such approaches rely on knowing all of the states of the model, which is not the case in practice. The work explored in this letter aims to develop a state observer to estimate Epileptor's unmeasurable variables, as well as reconstruct the respective so-called bursters. Furthermore, an alternative modeling is presented for enhancing the convergence speed of an observer. The results show that the proposed approach is efficient under two main conditions when the brain is undergoing a seizure and when a transition from the healthy to the epileptiform activity occurs.Neural networks are versatile tools for computation, having the ability to approximate a broad range of functions. An important problem in the theory of deep neural networks is expressivity; that is, we want to understand the functions that are computable by a given network. We study real, infinitely differentiable (smooth) hierarchical functions implemented by feedforward neural networks via composing simpler functions in two cases (1) each constituent function of the composition has fewer in puts than the resulting function and (2) constituent functions are in the more specific yet prevalent form of a nonlinear univariate function (e.g., tanh) applied to a linear multivariate function. We establish that in each of these regimes, there exist nontrivial algebraic partial differential equations (PDEs) that are satisfied by the computed functions. link3 These PDEs are purely in terms of the partial derivatives and are dependent only on the topology of the network. Conversely, we conjecture that such PDE constraints, once accompanied by appropriate nonsingularity conditions and perhaps certain inequalities involving partial derivatives, guarantee that the smooth function under consideration can be represented by the network. The conjecture is verified in numerous examples, including the case of tree architectures, which are of neuroscientific interest. Our approach is a step toward formulating an algebraic description of functional spaces associated with specific neural networks, and may provide useful new tools for constructing neural networks.Any visual system, biological or artificial, must make a trade-off between the number of units used to represent the visual environment and the spatial resolution of the sampling array. Humans and some other animals are able to allocate attention to spatial locations to reconfigure the sampling array of receptive fields (RFs), thereby enhancing the spatial resolution of representations without changing the overall number of sampling units. Here, we examine how representations of visual features in a fully convolutional neural network interact and interfere with each other in an eccentricity-dependent RF pooling array and how these interactions are influenced by dynamic changes in spatial resolution across the array. We study these feature interactions within the framework of visual crowding, a well-characterized perceptual phenomenon in which target objects in the visual periphery that are easily identified in isolation are much more difficult to identify when flanked by similar nearby objects. By separately simulating effects of spatial attention on RF size and on the density of the pooling array, we demonstrate that the increase in RF density due to attention is more beneficial than changes in RF size for enhancing target classification for crowded stimuli. Furthermore, by varying target and flanker spacing, as well as the spatial extent of attention, we find that feature redundancy across RFs has more influence on target classification than the fidelity of the feature representations themselves. Based on these findings, we propose a candidate mechanism by which spatial attention relieves visual crowding through enhanced feature redundancy that is mostly due to increased RF density.Rizzuto and Kahana (2001) applied an autoassociative Hopfield network to a paired-associate word learning experiment in which (1) participants studied word pairs (e.g., ABSENCE-HOLLOW), (2) were tested in one direction (ABSENCE-?) on a first test, and (3) were tested in the same direction again or in the reverse direction (?-HOLLOW) on a second test. The model contained a correlation parameter to capture the dependence between forward versus backward learning between the two words of a word pair, revealing correlation values close to 1.0 for all participants, consistent with neural network models that use the same weight for communication in both directions between nodes. We addressed several limitations of the model simulations and proposed two new models incorporating retrieval practice learning (e.g., the effect of the first test on the second) that fit the accuracy data more effectively, revealing substantially lower correlation values (average of .45 across participants, with zero correlation for some participants). In addition, we analyzed recall latencies, finding that second test recall was faster in the same direction after a correct first test. Only a model with stochastic retrieval practice learning predicted this effect. In conclusion, recall accuracy and recall latency suggest asymmetric learning, particularly in light of retrieval practice effects.

Patients who have experienced emotional abuse and neglect often develop psychiatric disorders in adulthood. However, whether emotional abuse, neglect, and mentalization abilities relate to one another and the role of possible mediators of this relationship in psychiatric patients are still unknown. We evaluated the potential role of affective temperament as a mediator of the relationship between emotional abuse and neglect and mentalization. We performed a cross-sectional study of 252 adult psychiatric inpatients. The Childhood Trauma Questionnaire, Mentalization Questionnaire, and Temperament Evaluation of Memphis, Pisa, Paris, and San Diego Autoquestionnaire (TEMPS-A) were administered. Results showed a significant indirect effect of emotional abuse and neglect on scores on the Mentalization Questionnaire through the TEMPS-A (b = 0.25, 95% confidence interval [0.143-0.375]), demonstrating that affective temperament mediates the relationship among emotional abuse, neglect, and mentalization impairment in psychiatric patients.