We show that similar methods are appropriate for learning unknown grammars from examples of their strings. TIle training algorithm is an incremental real-time, recurrent learning (RTRL) method that computes the complete gradient and updates the weights at the end of each string.

The two well known learning algorithms of recurrent neural networks are the back-propagation (Rumelhart & el al., Werbos) and the forward propagation (Williams and Zipser). The main drawback of back-propagation is its off-line backward path in time for error cumulation. This violates the online requirement in many practical applications. Although the forward propagation algorithm can be used in an online manner, the annoying drawback is the heavy computation load required to update the high dimensional sensitivity matrix (0( fir) operations for each time step). Therefore, to develop a fast forward algorithm is a challenging task.

We show that similar methods are appropriate for learning unknown grammars from examples of their strings. TIle training algorithm is an incremental real-time, recurrent learning (RTRL) method that computes the complete gradient and updates the weights at the end of each string.

The two well known learning algorithms of recurrent neural networks are the back-propagation (Rumelhart & el al., Werbos) and the forward propagation (Williamsand Zipser). The main drawback of back-propagation is its off-line backward path in time for error cumulation. This violates the online requirement in many practical applications. Although the forward propagation algorithmcan be used in an online manner, the annoying drawback is the heavy computation load required to update the high dimensional sensitivity matrix(0(fir) operations for each time step). Therefore, to develop a fast forward algorithm is a challenging task.

We show that similar methods are appropriate for learning unknown grammars from examples of their strings. TIle training algorithm is an incremental real-time, recurrent learning(RTRL) method that computes the complete gradient and updates the weights at the end ofeach string.

The neocognitron is a neural network for pattern recognition and feature extraction. An analog CCD parallel processing architecture developed at Lincoln Laboratory is particularly well suited to the computational requirements of shared-weight networks such as the neocognitron, and implementation of the neocognitron using the CCD architecture was simulated. A modification to the neocognitron training procedure, which improves network performance under the limited arithmetic precision that would be imposed by the CCD architecture, is presented.

We propose a new parallel-hierarchical neural network model to enable motor learning for simultaneous control of both trajectory and force.

A neural network architecture was designed for locating word boundaries and identifying words from phoneme sequences. This architecture was tested in three sets of studies. First, a highly redundant corpus with a restricted vocabulary was generated and the network was trained with a limited number of phonemic variations for the words in the corpus. Tests of network performance on a transfer set yielded a very low error rate. In a second study, a network was trained to identify words from expert transcriptions of speech.

A three-layered neural network model was used to explore the organization of the vestibulo-ocular reflex (VOR). The dynamic model was trained using recurrent back-propagation to produce compensatory, long duration eye muscle motoneuron outputs in response to short duration vestibular afferent head velocity inputs. The network learned to produce this response prolongation, known as velocity storage, by developing complex, lateral inhibitory interactions among the interneurons. These had the low baseline, long time constant, rectified and skewed responses that are characteristic of real VOR interneurons. The model suggests that all of these features are interrelated and result from lateral inhibition.

The neocognitron is a neural network for pattern recognition and feature extraction. An analog CCD parallel processing architecture developed at Lincoln Laboratory is particularly well suited to the computational requirements of shared-weight networks such as the neocognitron, and implementation of the neocognitron using the CCD architecture was simulated. A modification to the neocognitron training procedure, which improves network performance under the limited arithmetic precision that would be imposed by the CCD architecture, is presented.