1. Barnden, J.A. (1988). Conposit, a neural net system for high-level symbolic processing: overview of research and description of register-machine level. Memoranda in Computer and Cognitive Science, No. MCCS-88-145, Computing Research Laboratqry, New Mexico State University, Las Cruces, NM 88003.
2. Barnden, J.A. & Srinivas, K. (1991). Encoding techniques for complex information structures in connectionist systems. Connection Science, 3 (3), pp.263–309.
3. Baxnden, J.A. (1995). High-level reasoning, computational challenges for connectionism, and the Conposit solution. Applied Intelligence, 5 (2), pp.103–135.
4. Barnden, J.A. (1995). Complex symbol-processing in Conposit, a transiently localist connectionist architecture. In R. Sun & L. A. Bookman (Eds), Computational Architectures Integrating Neural and Symbolic Processes, pp.21–68. Norwell, MA: Kluwer Academic Publishers.
5. Shastri, L. & Ajjanagadde, V. (1993). From simple associations to systematic reasoning: a connectionist representation of rules, variables, and dynamic bindings using temporal synchrony. Behavioral and Brain Sciences, 16 (3), pp.417–494.