https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

▪ Abstract The prefrontal cortex has long been suspected to play an important role in cognitive control, in the ability to orchestrate thought and action in accordance with internal goals. Its neural basis, however, has remained a mystery. Here, we propose that cognitive control stems from the active maintenance of patterns of activity in the prefrontal cortex that represent goals and the means to achieve them. They provide bias signals to other brain structures whose net effect is to guide the flow of activity along neural pathways that establish the proper mappings between inputs, internal states, and outputs needed to perform a given task. We review neurophysiological, neurobiological, neuroimaging, and computational studies that support this theory and discuss its implications as well as further issues to be addressed

/pdf/an-integrative-theory-of-prefrontal-cortex-function-2j9unprn5f.pdf

An integrative theory of prefrontal cortex function

http://www.maths.qmul.ac.uk/%7Elatora/report_06.pdf

Complex networks: Structure and dynamics

Damage to the hippocampal system disrupts recent memory but leaves remote memory intact. The account presented here suggests that memories are first stored via synaptic changes in the hippocampal system, that these changes support reinstatement of recent memories in the neocortex, that neocortical synapses change a little on each reinstatement, and that remote memory is based on accumulated neocortical changes. Models that learn via changes to connections help explain this organization. These models discover the structure in ensembles of items if learning of each item is gradual and interleaved with learning about other items. This suggests that the neocortex learns slowly to discover the structure in ensembles of experiences. The hippocampal system permits rapid learning of new items without disrupting this structure, and reinstatement of new memories interleaves them with others to integrate them into structured neocortical memory systems.

Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory.

The theory of affordances

▪ Abstract The startling discovery by O'Keefe & Dostrovsky (Brain Res. 1971; 34: 171–75) that hippocampal neurons fire selectively in different regions or “place fields” of an environment and the subsequent development of the comprehensive theory by O'Keefe & Nadel (The Hippocampus as a Cognitive Map. Oxford, UK: Clarendon, 1978) that the hippocampus serves as a cognitive map have stimulated a substantial body of literature on the characteristics of hippocampal “place cells” and their relevance for our understanding of the mechanisms by which the brain processes spatial information. This paper reviews the major dimensions of the empirical research on place-cell activity and the development of computational models to explain various characteristics of place fields.

Spatial Processing in the Brain: The Activity of Hippocampal Place Cells

In this paper, we consider a heterogeneous team of UAVs drawn from several distinct classes and engaged in a search and destroy mission over an extended battlefield. Several different types of targets are considered. Some target locations are suspected a priori with a certain probability, while the others are initially unknown. During the mission, the UAVs perform Search, Confirm, Attack and Battle Damage Assessment (BDA) tasks at various locations. The target locations are detected gradually through search, while the tasks are determined in real-time by the actions of all UAVs and their results (e.g., sensor readings), which makes the task dynamics stochastic. The tasks must, therefore, be allocated to UAVs in real-time as they arise. Each class of UAVs has its own sensing and attack capabilities with respect to the different target types, so the need for appropriate and efficient assignment is paramount. We present a simple cooperative approach to this problem, based on distributed assignment mediated through centralized mission status information. Using this information, each UAV assesses the task opportunities available to it, and makes commitments through a phased incremental process. This produces a simple, flexible, scalable and inherently decentralizable method for task allocation. Concurrently, every UAV also monitors the degree to which various parts of the environment have been searched, and accommodates this information in planning its paths. We study the effect of various decision parameters, target distributions, and UAV team characteristics on the performance of our approach.

Cooperative real-time search and task allocation in UAV teams

This paper considers a heterogeneous team of cooperating unmanned aerial vehicles (UAVs) drawn from several distinct classes and engaged in a search and action mission over a spatially extended battlefield with targets of several types During the mission, the UAVs seek to confirm and verifiably destroy suspected targets and discover, confirm, and verifiably destroy unknown targets The locations of some (or all) targets are unknown a priori, requiring them to be located using cooperative search In addition, the tasks to be performed at each target location by the team of cooperative UAVs need to be coordinated The tasks must, therefore, be allocated to UAVs in real time as they arise, while ensuring that appropriate vehicles are assigned to each task Each class of UAVs has its own sensing and attack capabilities, so the need for appropriate assignment is paramount In this paper, an extensive dynamic model that captures the stochastic nature of the cooperative search and task assignment problems is developed, and algorithms for achieving a high level of performance are designed The paper focuses on investigating the value of predictive task assignment as a function of the number of unknown targets and number of UAVs In particular, it is shown that there is a tradeoff between search and task response in the context of prediction Based on the results, a hybrid algorithm for switching the use of prediction is proposed, which balances the search and task response The performance of the proposed algorithms is evaluated through Monte Carlo simulations

/pdf/balancing-search-and-target-response-in-cooperative-unmanned-ym7vvftdru.pdf

Balancing search and target response in cooperative unmanned aerial vehicle (UAV) teams

The whole-brain functional connectivity (FC) pattern obtained from resting-state functional magnetic resonance imaging data are commonly applied to study neuropsychiatric conditions such as autism spectrum disorder (ASD) by using different machine learning models. Recent studies indicate that both hyper- and hypo- aberrant ASD-associated FCs were widely distributed throughout the entire brain rather than only in some specific brain regions. Deep neural networks (DNN) with multiple hidden layers have shown the ability to systematically extract lower-to-higher level information from high dimensional data across a series of neural hidden layers, significantly improving classification accuracy for such data. In this study, a DNN with a novel feature selection method (DNN-FS) is developed for the high dimensional whole-brain resting-state FC pattern classification of ASD patients versus typical development (TD) controls. The feature selection method is able to help the DNN generate low dimensional high-quality representations of the whole-brain FC patterns by selecting features with high discriminating power from multiple trained sparse auto-encoders. For the comparison, a DNN without the feature selection method (DNN-woFS) is developed, and both of them are tested with different architectures (i.e., with different numbers of hidden layers/nodes). Results show that the best classification accuracy of 86.36% is generated by the DNN-FS approach with 3 hidden layers and 150 hidden nodes (3/150). Remarkably, DNN-FS outperforms DNN-woFS for all architectures studied. The most significant accuracy improvement was 9.09% with the 3/150 architecture. The method also outperforms other feature selection methods, e.g., two sample t-test and elastic net. In addition to improving the classification accuracy, a Fisher’s score-based biomarker identification method based on the DNN is also developed, and used to identify 32 FCs related to ASD. These FCs come from or cross different pre-defined brain networks including the default-mode, cingulo-opercular, frontal-parietal and cerebellum. Thirteen of them are statically significant between ASD and TD groups (two sample t test p-value < 0.05) while nineteen of them are not. The relationship between the statically significant FCs and the corresponding ASD behavior symptoms is discussed based on the literature and clinician’s expert knowledge. Meanwhile, the potential reason of obtaining nineteen FCs which are not statistically

/pdf/diagnosing-autism-spectrum-disorder-from-brain-resting-state-3tto4179it.pdf

Diagnosing Autism Spectrum Disorder from Brain Resting-State Functional Connectivity Patterns Using a Deep Neural Network with a Novel Feature Selection Method

Ali A. Minai

Papers

Spatial Processing in the Brain: The Activity of Hippocampal Place Cells

Cooperative real-time search and task allocation in UAV teams

Balancing search and target response in cooperative unmanned aerial vehicle (UAV) teams

Diagnosing Autism Spectrum Disorder from Brain Resting-State Functional Connectivity Patterns Using a Deep Neural Network with a Novel Feature Selection Method

Efficient associative memory using small-world architecture