Knowm Tech, LLC Patent applications |
Patent application number | Title | Published |
20140156576 | MEMRISTIVE NEURAL PROCESSOR UTILIZING ANTI-HEBBIAN AND HEBBIAN TECHNOLOGY - An AHaH (Anti-Hebbian and Hebbian) apparatus for use in electronic circuits. Such an AHaH apparatus can include one or more meta-stable switches, and one or more differential pairs of output electrodes, wherein each electrode among each differential pair of output electrodes can include one or more input lines coupled thereto via one or more of the meta-stable switch. | 06-05-2014 |
20130289902 | ANOMALY DETECTION UTILIZING ENERGY FLOW NETWORKS - A fabric of cores can be configured to spontaneously organize internal structure that mirrors the spatial-temporal causal structure of the data stream that is injected into the fabric. The mechanism is that of a self-organizing energy dissipating structure such that the energetic source is the injected signals and the energetic sink is the collisions of signals in cores. An adaptive routing architecture is further possible such that energy is preferentially allocated in the direction of maximal energy sink. By measuring the energy dissipation rate, anomalies may be detected by comparing to a set threshold. | 10-31-2013 |
20130258905 | SELF-EVOLVABLE LOGIC FABRIC - Methods and systems for achieving self-organized growth of a logic pathway. A number of hardware modules that represents a core can be configured and communicated via a packet routing architecture. Each core includes a plurality of sub-modules that interact dynamically to a growth algorithm. A flow network can be created between a sensor input and a prediction of a desired sensor input and a link can be formed between a regularity within a core and another core via a link-flow-selection process. A digital data packet can be transmitted between the cores for communicating activation of the regularity and to exchange energy. Such physically-self organized circuit fabric system interacts dynamically to a growth algorithm that takes the input to produce a desired output and continuously self-repair and/or heal if damaged. | 10-03-2013 |
20130218815 | METHODS AND SYSTEMS FOR FEATURE EXTRACTION - A method and system for extracting feature utilizing an AHaH module (Anti-Hebbian and Hebbian). A sparse input data stream can be presented to a synaptic matrix of a collection of AHaH nodes associated with the AHaH module. The AHaH module operates an AHaH plasticity rule via an evaluate phase and a feedback phase cycle. A bias input line can be modulated such that a bias weight do not receive a Hebbian portion of the weight update during the feedback phase in order to prevent occupation of a null state. The input space can be bifurcated when the AHaH nodes fall randomly into an attractor state. The output of the AHaH module that forms a stable bit pattern can then be provided as an input to a content-addressable memory for generating a maximally efficient binary label. | 08-22-2013 |