Many different discrete-time recurrent neural network architectures have been proposed. However, there has been virtually no effort to compare these arch:tectures experimentally. In this paper we review and categorize many of these architectures and compare how they perform on various classes of simple problems including grammatical inference and nonlinear system identification.

We describe a system that can track a hand in a sequence of video frames and recognize hand gestures in a user-independent manner. The system locates the hand in each video frame and determines if the hand is open or closed. The tracking system is able to track the hand to within 10 pixels of its correct location in 99.7% of the frames from a test set containing video sequences from 18 different individuals captured in 18 different room environments. The gesture recognition network correctly determines if the hand being tracked is open or closed in 99.1 % of the frames in this test set. The system has been designed to operate in real time with existing hardware.

Many different discrete-time recurrent neural network architectures have been proposed. However, there has been virtually no effort to compare these arch:tectures experimentally. In this paper we review and categorize many of these architectures and compare how they perform on various classes of simple problems including grammatical inference and nonlinear system identification.

Many different discrete-time recurrent neural network architectures havebeen proposed. However, there has been virtually no effort to compare these arch:tectures experimentally. In this paper we review and categorize many of these architectures and compare how they perform on various classes of simple problems including grammatical inference and nonlinear system identification.

We describe a system that can track a hand in a sequence of video frames and recognize hand gestures in a user-independent manner. The system locates the hand in each video frame and determines if the hand is open or closed. The tracking system is able to track the hand to within 10 pixels of its correct location in 99.7% of the frames from a test set containing video sequences from 18 different individualscaptured in 18 different room environments. The gesture recognition network correctly determines if the hand being tracked is open or closed in 99.1 % of the frames in this test set. The system has been designed to operate in real time with existing hardware.

This paper describes the use of a convolutional neural network to perform address block location on machine-printed mail pieces. Locating the address block is a difficult object recognition problem because there is often a large amount of extraneous printing on a mail piece and because address blocks vary dramatically in size and shape. We used a convolutional locator network with four outputs, each trained to find a different corner of the address block. A simple set of rules was used to generate ABL candidates from the network output. The system performs very well: when allowed five guesses, the network will tightly bound the address delivery information in 98.2% of the cases.

Although there are many ways to measure efficiency, we shall be concerned with node complexity, which as its name implies, is a calculation of the required number of nodes. Node complexity is a useful measure of efficiency since the amount of resources required to implement or even simulate a recurrent neural network is typically related to the number of nodes. Node complexity can also be related to the efficiency of learning algorithms for these networks and perhaps to their generalization ability as well. We shall focus on the node complexity of recurrent neural network implementations of finite state machines (FSMs) when the nodes of the network are restricted to threshold logic units.

This paper describes the use of a convolutional neural network to perform address block location on machine-printed mail pieces. Locating the address block is a difficult object recognition problem because there is often a large amount of extraneous printing on a mail piece and because address blocks vary dramatically in size and shape. We used a convolutional locator network with four outputs, each trained to find a different corner of the address block. A simple set of rules was used to generate ABL candidates from the network output. The system performs very well: when allowed five guesses, the network will tightly bound the address delivery information in 98.2% of the cases.

We prove that the so called "loading problem" for (recurrent) neural networks is unsolvable. This extends several results which already demonstrated that training and related design problems for neural networks are (at least) NPcomplete. Our result also implies that it is impossible to find or to formulate a universal training algorithm, which for any neural network architecture could determine a correct set of weights. For the simple proof of this, we will just show that the loading problem is equivalent to "Hilbert's tenth problem" which is known to be unsolvable.

Although there are many ways to measure efficiency, we shall be concerned with node complexity, which as its name implies, is a calculation of the required number of nodes. Node complexity is a useful measure of efficiency since the amount of resources required to implement or even simulate a recurrent neural network is typically related to the number of nodes. Node complexity can also be related to the efficiency of learning algorithms for these networks and perhaps to their generalization ability as well. We shall focus on the node complexity of recurrent neural network implementations of finite state machines (FSMs) when the nodes of the network are restricted to threshold logic units.