S ome researchers in the computational sciences have considered music computation, including music reproduction and generation, as a dynamic system, i.e., a feedback process. The key element is that the state of the musical system depends on a history of past states. Recurrent (neural) networks have been deployed as models for learning musical processes. We first present a tutorial discussion of recurrent networks, covering those that have been used for music learning. Following this, we examine a thread of development of these recurrent networks for music computation that shows how more intricate music has been learned as the state of the art in recurrent networks improves. We present our findings that show that a long short-term memory recurrent network, with new representations that include music knowledge, can learn musical tasks, and can learn to reproduce long songs. Then, given a reharmonization of the chordal structure, it can generate an improvisation.

No abstract

No abstract

S performance. In this work we focus on two skills, namely robotic assembly and balancing and on two classic tasks to develop these skills via Ieaming: the peg-in-hole insertion task, and the ball balancing task. A stochastic real-valued (SRV) reinforcement leaming algorithm is described and used for leam-is with the Conipiiter Sc,ienc,e Depurtnietit, Utii\wsity of Massachusetts. Amhcr..>t. MA 01003. Enruil: ,.ijuyku-mar@cs.umass.edu. J.A. Fixnkliii und H . Benhrulrinr are Mith GTE Labor-utories Incorporated, 40 S y l~m Roud. Wulthuni. MA 02254. Email: ,$runkliri@gte.cwn and hhc~rihruhini~,~tc..c.om. The w w k of V: Gullapalli was siippor.ted by firriding to A. Barto by the AFOSR.Skilled behavior involves the effective use of knowledge in execution or performance. A skill may require dexterity or coordination, and generally develops over time through leaming. This work focuses on employing leaming to enable a robot to acquire skills, particularly physical skills where leaming control is required. The requirements are i) dealing with nonlinearity/complex dynamics, ii) achieving robust performance under

Ab8tract-I have worked on several teams' that have applied artificial neural networks (ANNs) to modelling and/or controlling physical systems. My goal is to expose these applications to ANN researchers. This paper describes three of these systems, two in wireless communication and one in manufacturing. The examples are all actual hardware systems. The two wireless communication systems are small testbeds that were devised in our Real-Time Learning Laboratory at GTE Laboratories. The manufacturing plant is an actual site. ANNs are able to learn models of each of these systems. Controllers can use these models in various ways. I describe these controllers and draw parallels between the applications.