Abstract: Aspects of the present disclosure provide methods and apparatus for allocating memory in an artificial nervous system simulator implemented in hardware. According to certain aspects, memory resource requirements for one or more components of an artificial nervous system being simulated may be determined and portions of a shared memory pool (which may include on-chip and/or off-chip RAM) may be allocated to the components based on the determination.

Abstract: Methods and apparatus are provided for using a breakpoint determination unit to examine an artificial nervous system. One example method generally includes operating at least a portion of the artificial nervous system; using the breakpoint determination unit to detect that a condition exists based at least in part on monitoring one or more components in the artificial nervous system; and at least one of suspending, examining, modifying, or flagging the operation of the at least the portion of the artificial nervous system, based at least in part on the detection.

Abstract: An e-learning system has a local classroom with an instructor station and a microphone and a local student station with a microphone, a remote classroom with an instructor display and a student station with a microphone, and planar displays and video cameras in each of the classrooms, the remote and local classrooms connected over a network, with a server monitoring feeds and enforcing exclusive states, such that audio and video feeds are managed in a manner that video and audio of the instructor, the local students and the first remote students, as seen and heard either directly or via speakers and displays by each of the instructor, the local students and the remote students presents to each as though all are interacting in the same room.

Abstract: A server computing system selects a machine learning kernel from a plurality of machine learning kernels using a plurality of training documents. The server computing system identifies a plurality of testing documents from a plurality of electronic discovery documents based on the plurality of training documents. For each of the plurality of machine learning kernels and for each testing document in the plurality of testing documents, the server computing system determines a class of the testing document using a default value for each of a plurality of parameters for the machine learning kernel and evaluates a goodness of fit of the machine learning kernel for the testing document. The server computing system selects a machine learning kernel from the plurality of machine learning kernels and determines a value for at least one of the plurality of parameters for the selected machine learning kernel using a goodness of fit test.

Abstract: Methods and apparatus are provided for determining synapses in an artificial nervous system based on connectivity patterns. One example method generally includes determining, for an artificial neuron, an event has occurred; based on the event, determining one or more synapses with other artificial neurons based on a connectivity pattern associated with the artificial neuron; and applying a spike from the artificial neuron to the other artificial neurons based on the determined synapses. In this manner, the connectivity patterns (or parameters for determining such patterns) for particular neuron types, rather than the connectivity itself, may be stored. Using the stored information, synapses may be computed on the fly, thereby reducing memory consumption and increasing memory bandwidth. This also saves time during artificial nervous system updates.

Abstract: Methods and apparatus are provided for implementing delays in an artificial nervous system. Synaptic and/or axonal delays between a post-synaptic artificial neuron and one or more pre-synaptic artificial neurons may be accounted for at the post-synaptic artificial neuron. One example method for managing delay between neurons in an artificial nervous system generally includes receiving, at a post-synaptic artificial neuron, input current values from one or more pre-synaptic artificial neurons; accounting for delays between the one or more pre-synaptic artificial neurons and the post-synaptic artificial neuron at the post-synaptic artificial neuron; and determining a state of the post-synaptic artificial neuron based at least in part on at least a portion of the input current values, according to the accounting.

Abstract: Certain aspects of the present disclosure support a technique for efficient implementation of neural population diversity in neural systems. A set of parameters for each class of artificial neurons of a plurality of classes can be stored in a storage medium. A generator can be configured to obtain noise parameters for each class of artificial neurons in the neural system. After that, the noise parameters can be combined with the set of parameters for each class of artificial neurons to obtain a dithered set of parameters for each class of artificial neurons. The dithered set of parameters can be stored for each class of artificial neurons to be used for a neuron model for the artificial neurons that emulates behavior of the artificial neurons in the neural system.

Abstract: Certain aspects of the present disclosure support operating simultaneously multiple super neuron processing units in an artificial nervous system, wherein a plurality of artificial neurons is assigned to each super neuron processing unit. The super neuron processing units can be interfaced with a memory for storing and loading synaptic weights and plasticity parameters of the artificial nervous system, wherein organization of the memory allows contiguous memory access.

Abstract: Systems and methods for harvesting dissipated heat from integrated circuits (ICs) in electronic devices into electrical energy for providing power for the electronic devices are disclosed. In one embodiment, energy transferred from one or more ICs in the form of dissipated heat is harvested to convert at least a portion of this dissipated heat into electricity. This power can be used to provide power to the ICs to reduce overall power consumption by the electronic device. The harvested dissipated heat can be supplied to ICs in the electronic device to provide power to the ICs. Alternatively, or in addition, the harvested dissipated heat can be stored in an energy storage device to provide power to the ICs at a later time.

Abstract: In various embodiments, a semantic space associated with a corpus of electronically stored information (ESI) may be created and used for concept searches. Documents (and any other objects in the ESI, in general) may be represented as vectors in the semantic space. Vectors may correspond to identifiers, such as, for example, indexed terms. The semantic space for a corpus of ESI can be used in information filtering, information retrieval, indexing, and relevancy rankings.

Abstract: Certain aspects of the present disclosure provide techniques for time management and scheduling of synchronous neural processing on a cluster of processing nodes. A slip (or offset) may be introduced between processing nodes of a distributed processing system formed by a plurality of interconnected processing nodes, to enable faster nodes to continue processing without waiting for slower nodes to catch up. In certain aspects, a processing node, after completing each processing step, may check for received completion packets and apply a defined constraint to determine whether it may start processing a subsequent step or not.

Abstract: A system for protecting data managed in a cloud-computing network from malicious data operations includes an Internet-connected server and software executing on the server from a non-transitory physical medium, the software providing a first function for generating one or more security tokens that validate one or more computing operations to be performed on the data, a second function for generating a hash for each token generated, the hash detailing, in a secure fashion, the operation type or types permitted by the one or more tokens, a third function for brokering two-party signature of the one or more tokens, and a fourth function for dynamically activating the one or more signed tokens for a specific time window required to perform the operations permitted by the token.

Abstract: Certain aspects of the present disclosure support techniques for collecting system information in a network on a chip (NoC). A dedicated packet may be transmitted from a source node to a destination node. As it traverses through the NoC, the dedicated packet may collect information from various nodes, which may be made available by the destination node. The collected information may be used in an effort to detect failures and collect statistics regarding the NoC.

Abstract: Certain aspects of the present disclosure support a technique for optimized representation of variables in neural systems. Bit-allocation for neural signals and parameters in a neural network described in the present disclosure may comprise allocating quantization levels to the neural signals based on at least one measure of sensitivity of a pre-determined performance metric to quantization errors in the neural signals, and allocating bits to the parameters based on the at least one measure of sensitivity of the pre-determined performance metric to quantization errors in the parameters.

Abstract: Certain embodiments of the present disclosure support techniques for simplified hardware implementation of the reward-modulated spike-timing-dependent plasticity (STDP) learning rule in networks of spiking neurons.

Abstract: The present disclosure proposes implementation of a three-memristor synapse where an adjustment of synaptic strength is based on Spike-Timing-Dependent Plasticity (STDP) with dopamine signaling.

Abstract: Methods and systems for searching e-mails are disclosed. In one embodiment, a method for displaying information associated with electronic messages includes receiving information associated with a plurality of e-mails in response to a search query. Each e-mail in the plurality of e-mails is categorized according to a set of categories. Relevance is determined of each e-mail in the plurality of e-mails. The plurality of e-mails are then displayed using a graphical user interface according to the set of categories and the relevance of each e-mail. Input may be received from a user indicative of a tag. The tag may be associated with at least one of the plurality of e-mails and displayed to assist in review.

Abstract: A system for providing network-based interactive learning including at least one network-connected passive server and at least one network-connected active server, each executing software from a non-transitory physical medium. The passive server provides a log-in function providing log-in for a student for a specific learning session, a provisioning function downloading reference materials for the particular learning session to the student's appliance after log-in, and a switch function connecting the student's appliance to the at least one active server after the reference material is downloaded.

Abstract: Techniques are provided for automatic sampling evaluation. An automatic sampling evaluation system enables users to evaluate convergence of one or more search processes. For example, given a set of searches that were validated by human review, a system can implement a retrieval process that samples one or more non-retrieved collections. Each individual document's similarity in the one or more non-retrieved collections is automatically evaluated to other documents in any retrieved sets. Given a goal of achieving a high recall, documents with high similarity can then be analyzed for additional noun phrases that may be used for a next iteration of a search. Convergence can be expected if the information gain in the new feedback loop is less than previous iterations, and if the additional documents identified are below a certain threshold document count.

Abstract: A set of trigrams can be generated for each document in a plurality of documents processed by an e-discovery system. Each trigram in the set of trigrams for a given document is a sequence of three terms in the given document. A set of trigrams for each similar document is then determined based on the set of trigrams for the original document. To facilitate identification of the similar documents, a full text index is then generated for the plurality of documents and the set of trigrams for each document are indexed into the full text index, as individual terms. Queries can be generated into the full text index based on trigrams of a document to determine other similar or near-duplicate documents. After a set of potentially similar documents are identified, a separate distance criteria can be applied to evaluate the level of similarity between the two documents in an efficient way.