Training a network with ternary weights using the CHIR algorithm
暂无分享,去创建一个
A modification of the binary weight CHIR algorithm is presented, whereby a zero state is added to the possible binary weight states. This method allows solutions with reduced connectivity to be obtained, by offering disconnections in addition to the excitatory and inhibitory connections. The algorithm has been examined via extensive computer simulations for the restricted cases of parity, symmetry, and teacher problems, which show convergence rates similar to those presented for the binary CHIR2 algorithm, but with reduced connectivity. Moreover, this method expands the set of problems solvable via the binary weight network configuration with no additional parameter requirements.
[1] Eytan Domany,et al. Learning by CHIR without Storing Internal Representations , 1990, Complex Syst..
[2] H. Gutfreund,et al. Capacity of neural networks with discrete synaptic couplings , 1990 .
[3] Eytan Domany,et al. Learning by Choice of Internal Representations , 1988, Complex Syst..
[4] David Saad,et al. Learning by Choice of Internal Representations: An Energy Minimization Approach , 1990, Complex Syst..