Titlebook: On the Construction of Artificial Brains; Ulrich Ramacher,Christoph Malsburg Book 20101st edition Springer-Verlag Berlin Heidelberg 2010 E

deviate

好忠告人

争议的苹果

Elementary Circuits for Neurons, Synapses, and Photosensors, membrane of a neuron. A threshold switch with hysteresis determines the state variable with two values . ∈ {0,1} of neuron . by comparing the accumulator potential with a reference voltage. At the time of firing, . takes on the value 1 during the time span ., which is achieved by discharging the ca

花束

荧光

Architecture and Chip Design of the Feature Recognizer, behind the application of this technology is illustrated in Figure 14.1..Several chips are stacked on to a base chip. The stack technology allows the placement of vertical interconnections in high density even in the inner area of the chip. The image information is transmitted optically to the CMOS

空气传播

Architecture and Chip Design of the Feature Detector,ection topology to realise arbitrary feature detectors, at a faithful reproduction of the simulated individual or group behaviour of neurons and synapses, and at low power dissipation as well as the integration of image sensor pixel cells in order to directly supply the feature detectors with input

Anthropoid

3D Stacking Technology,ted layers for each subtask. Finally, it was shown how dedicated VLSI circuits supporting these subtasks can be implemented. The integration of particular components (CMOS imager, feature cascade, object recogniser) into a system poses further questions, however. Particularly, the problem of interco

赔偿

Architecture of First Generation Vision Cube,retina, possesses 8 orientations per resolution plane and 5 resolution planes and recognises distant-invariantly up to 1000 objects each featuring 10 zones. The neural architecture of this vision system is described in chapters 6-9.

旋转一周

End,tors/recognisers for 1000 objects, as described here. For the recognition of one million objects, we would have to reckon with 31 ·10. neurons, ( 3.1 percent) and 135 ·10. synapses (0.013 percent). After all, if we imagine the one million objects related to each other by means of a gigantic correlat

灰心丧气