Abstract: A method for improved thinning or skeletonizing handwritten characters or other variable-line-width images. The method scans a template set over the image to be thinned. Each template has a specific arrangement of dark and light pixels. At least one of those templates includes either more than three pixels per row or more than three rows of pixels. An odd number is good choice. Moreover, the templates are chosen so that each template can unconditionally delete image pixels without consideration of the effect of such deletions on the behavior of the other templates. Thus the templates are independent of each other.

Abstract: Highly accurate, reliable optical character recognition is afforded by a layered network having several layers of constrained feature detection wherein each layer of constrained feature detection includes a plurality of constrained feature maps and a corresponding plurality of feature reduction maps. Each feature reduction map is connected to only one constrained feature map in the same layer for undersampling that constrained feature map. Units in each constrained feature map of the first constrained feature detection layer respond as a function of a corresponding kernel and of different portions of the pixel image of the character captured in a receptive field associated with the unit.

Abstract: Highly accurate, reliable optical character recognition is afforded by a hierarchically layered network having several layers of parallel constrained feature detection for localized feature extraction followed by several fully connected layers for dimensionality reduction. Character classification is also performed in the ultimate fully connected layer. Each layer of parallel constrained feature detection comprises a plurality of constrained feature maps and a corresponding plurality of kernels wherein a predetermined kernel is directly related to a single constrained feature map. Undersampling is performed from layer to layer.

Abstract: Neural network type information processing devices have been proposed. In these devices, a matrix structure is utilized with impedance at the matrix intersection points. It has been found that excellent versatility in design is achieved by utilizing photoconductors at these intersection points and thus affording the possibility of controlling impedance by, in turn, controlling the level of incident light.

Abstract: A highly interconnected analog network is constructed with inter-neurons that account for energy function terms of order greater than two. The network comprises analog amplifiers that are connected with a resistive interconnection matrix which connects each amplifier output to the input of all other amplifiers. The connections embodied in the matrix are achieved with conductances whose values are computed in accordance with the set of problem restrictions, while the cost variables of the problem which are to be minimized are incorporated in the input signals.

Abstract: A read/write system which reduces access time in optical disc apparatus is disclosed. The head includes an array of lenses which covers a substantial portion of the radius of the disc. Access of a particular disc track is achieved by deflection of the reading beam, rather than by any physical movement of the head. For read-out, the array focuses light reflected from the disc onto a corresponding array of photodetectors.

Abstract: A self-aligning technique is used to produce small area junctions such as small area Josephson junctions. A base layer having a thickness corresponding to one dimension of the junction is first deposited. An insulating material is then deposited from a source positioned so that the base layer itself masks its edge from the insulator being formed. This procedure coats the base layer with an insulator, but leaves an edge of this layer free of insulation. A junction is then completed on this uncoated edge.

Abstract: The use of a specific two-layer resist composition with a more sensitive and thicker resist as the lower layer allows the production of lines on the order of 400 A in width separated by spaces on the order of 400 A.

Abstract: The transfer characteristic of nonhysteretic Josephson junction gates (G) is sharpened and desired switching behavior free from resetting requirements is achieved by a positive feedback scheme (FIGS. 5, 8-9) in which the gate is made to be responsive to current flow in the output line (20). Specific applications to three-junction interferometers (FIG. 5) are described as are various means for rendering the gate responsive to the output, i.e., magnetically coupling the output line to the gate (FIGS. 5, 8), adding a portion of the output current to the control line (FIG. 9), and injecting a portion of the output current directly into the gate (FIG. 10).

Abstract: Superconductor junctions adaptable for applications such as logic circuitry and magnetic flux detection are disclosed. These junctions utilize superconducting electrodes with a semiconductor barrier composed of a binary composition of germanium and tin. The composition of this binary composition strongly affects the electrical properties of the device. For example, when using two Sn electrodes, if the Sn/Ge ratio in the barrier is changed from 1:4 to 1:1 for a thickness of 600 A, the electrical properties of the junction transform from hysteretic to non-hysteretic characteristics.