Learn More
We present an application of back-propagation networks to handwritten digit recognition. Minimal preprocessing of the data was required, but architecture of the network was highly constrained and speciically designed for the task. The input of the network consists of normalized images of isolated digits. The method has 1% error rate and about a 9% reject(More)
This paper describes the construction of a system that recognizes hand-printed digits, using a combination of classical techniques and neural-net methods. The system has been trained and tested on real-world data, derived from zip codes seen on actual U.S. Mail. The system rejects a small percentage of the examples as unclassifiable, and achieves a very low(More)
The authors describe a complementary metal-oxide-semiconductor (CMOS) very-large-scale integrated (VLSI) circuit implementing a connectionist neural-network model. It consists of an array of 54 simple processors fully interconnected with a programmable connection matrix. This experimental design tests the behavior of a large network of processors integrated(More)
A general-purpose, fully interconnected neural-net chip was used to perform computationally intensive tasks for handwritten digit recognition. The chip has nearly 3000 programmable connections, which can be set for template matching. The templates can be reprogrammed as needed during the recognition sequence. The recognition process proceeds in four major(More)
MOS charge storage has been demonstrated as an effective method to store the weights in VLSI implementations of neural network models by several workers 2. However, to achieve the full power of a VLSI implementation of an adaptive algorithm, the learning operation must built into the circuit. We have fabricated and tested a circuit ideal for this purpose by(More)
10 alignment span. For example in Figure 12, the hypothesized word, " STCTES " is selected with a maximum signal of 0.254. The next fan-out will begin with " L " , starting from the position in the text line, " lnOrdertOFOr ". If no hypothesized words are selected within the current fan-out, then the processing advances one character in the text line, and(More)
of Japanese Kanji using principal component analysis as a preprocessor to an articial neural network. learning for multi-layer feed-forward neural networks using the conjugate gradient method. 28 be rejected for OCR to suceed. Another way of considering the rejection problem is to consider the number of images that are near any 32 by 32 binary image in(More)
  • 1