The Fredkin Challenge in AI Research and Applications at Chandrasekaran, B. see nlso Hendler, Match, 2(2): Summer 1981, 30-33.

Integrated Language and Vision Systems, Scholarship Travel Program If you are interested in assisting AAAI at the national conference, New Mexico State University, Continued please contact AAAI at volunteer Dec. 1991 AAAI announces the continuation of @aaai.org. All inquiries should 1991 IFIP/KR Workshop its scholarship travel program for students include your name, address, telephone, Eleventh International Workshop on who want to attend the National advisor's name, and email Distributed Artificial Intelligence, Conference on Artificial Intelligence address. All requests to volunteer at Glen Arbor, Michigan, February 1992 in San Jose, California, 12-17 July AAAI-92 must be received by the 1992. First International Conference on and (2) are members of April 3 AAAI-92 Scholarship AI Planning Systems, University of AAAI. In addition, repeat scholarship Application Deadline Maryland, June 1992 applicants must have fulfilled the April 29 Al Magazine Summer Issue The Third International Conference volunteer and reporting requirements Calendar Deadline on Principles of Knowledge Representation for previous awards.

The workshop "Advances in Interfacing Production Systems with the Real World" was designed to bring together researchers from around the world to focus on the problem of integrating production systems into industrial environments. It was held on 25 August 1991 in Sydney, Australia, in conjunction with the Twelfth International Joint Conference on Artificial Intelligence (IJCAI-91). Nine papers were accepted for the proceedings, and six of them were discussed at the workshop.

My Ph.D. thesis (Ward 1992, 1991)1 addressed the task of generating natural language utterances. It was motivated by two difficulties in scaling up existing generators. Current generators only accept input that are relatively poor in information, such as feature structures or lists of propositions; they are unable to deal with input rich in information, as one might expect from, for example, an expert system with a complete model of its domain or a natural language understander with good inference ability. Current generators also have a very restricted knowledge of language -- indeed, they succeed largely because they have few syntactic or lexical options available (McDonald 1987) -- and they are unable to cope with more knowledge because they deal with interactions among the various possible choices only as special cases. To address these and other issues, I built a system called FIG (flexible incremental generator). FIG is based on a single associative network that encodes lexical knowledge, syntactic knowledge, and world knowledge. Computation is done by spreading activation across the network, supplemented with a small amount of symbolic processing. Thus, FIG is a spreading activation or structured connectionist system (Feldman et al. 1988).

Chalasani et al. show that this problem is Korf (1985) presents a method for learning macrooperators in NP, but NPcompleteness is open. Tadepalli (1991a, and shows that the method is applicable 1991b) shows how macro tables are polynomially PAClearnable to serially decomposable problems.

We present a new connectionist planning method [TML90]. By interaction with an unknown environment, a world model is progressively constructed using gradient descent. For deriving optimal actions with respect to future reinforcement, planning is applied in two steps: an experience network proposes a plan which is subsequently optimized by gradient descent with a chain of world models, so that an optimal reinforcement may be obtained when it is actually run. The appropriateness of this method is demonstrated by a robotics application and a pole balancing task.

The Hopfield network (Hopfield, 1982,1984) provides a simple model of an associative memory in a neuronal structure. This model, however, is based on highly artificial assumptions, especially the use of formal-two state neurons (Hopfield, 1982) or graded-response neurons (Hopfield, 1984).

Combining neuropharmacological experiments with computational modeling, we have shown that cholinergic modulation may enhance associative memory function in piriform (olfactory) cortex. We have shown that the acetylcholine analogue carbachol selectively suppresses synaptic transmission between cells within piriform cortex, while leaving input connections unaffected. When tested in a computational model of piriform cortex, this selective suppression, applied during learning, enhances associative memory performance.

We present a new connectionist planning method [TML90]. By interaction with an unknown environment, a world model is progressively constructed using gradient descent. For deriving optimal actions with respect to future reinforcement, planning is applied in two steps: an experience network proposes a plan which is subsequently optimized by gradient descent with a chain of world models, so that an optimal reinforcement may be obtained when it is actually run. The appropriateness of this method is demonstrated by a robotics application and a pole balancing task.

The Hopfield network (Hopfield, 1982,1984) provides a simple model of an associative memory in a neuronal structure. This model, however, is based on highly artificial assumptions, especially the use of formal-two state neurons (Hopfield, 1982) or graded-response neurons (Hopfield, 1984).