Dynamic Binary Neural Networks Research Articles

Dynamic binary neural networks with time-variant parameters and switching of desired periodic orbits

This paper studies 3-layer dynamic binary neural networks characterized by binary connection parameters and the signum activation function. The connection parameters and the number of hidden neurons are time-variant. The dynamics is described by a non-autonomous difference equation of binary state variables and the network can generate various periodic orbits of binary vectors. First, we present a simple synthesis method that guarantees storage of desired multiple periodic orbits and switching of the periodic orbits through desired entrances. Second, as a basic step to engineering applications, we present an FPGA based hardware prototype. The hardware can realize switching of various periodic orbits experimentally and typical examples are demonstrated. The switching of periodic orbits is applicable to switching of walking patterns in robotics and variable output of switching power converters.

Guaranteed storage and stabilization of desired binary periodic orbits in three-layer dynamic binary neural networks

This paper presents three-layer dynamic binary neural networks characterized by ternary connection parameters and the signum activation function. The dynamics is described by a difference equation of binary state variables. Depending on the parameters, the network can generate various binary periodic orbits. We give two main theoretical results. First, when a desired periodic orbit is given, we can set the parameters that guarantee storage and local stability of the periodic orbit. The stability is related to error correction of various binary signals in engineering applications. Second, if a part of the connection parameters becomes zero then stability of the periodic orbit becomes very strong. In this case, all the initial states fall directly into the periodic orbit.

Theoretical analysis of dynamic binary neural networks with simple sparse connection

This paper studies dynamic binary neural networks with simple sparse connection such that each neuron transforms three binary inputs to one binary output via three binary branches. First, it is proven theoretically that rotation-type periodic orbits can be stored into the networks and local stability of the stored orbits is very strong. If the local stability is very strong, the networks can remove any 1-bit error and make the periodic orbits robust. Second, an FPGA-based implementation is presented where the neurons are realized by simple majority decision circuits and the binary positive/negative connections are realized by direct/inverter connections. Using the hardware, typical periodic orbits are confirmed experimentally. The simple FPGA-based implementation is basic to realize engineering applications of the networks such as control signals of switching circuits.

Erratum: Simple Feature Quantities for Analysis of Periodic Orbits in Dynamic Binary Neural Networks [IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences Vol. E101.A (2018) , No. 4 pp.727-730

Erratum: Simple Feature Quantities for Analysis of Periodic Orbits in Dynamic Binary Neural Networks [IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences Vol. E101.A (2018) , No. 4 pp.727-730

Simple Feature Quantities for Analysis of Periodic Orbits in Dynamic Binary Neural Networks

Simple Feature Quantities for Analysis of Periodic Orbits in Dynamic Binary Neural Networks

Stabilization of desired periodic orbits in dynamic binary neural networks

A dynamic binary neural network is a simple two-layer network with a delayed feedback and is able to generate various binary periodic orbits. The network is characterized by the signum activation function, ternary connection parameters, and integer threshold parameters. The ternary connection brings benefits to network hardware and to computation costs in numerical analysis. In order to stabilize a desired binary periodic orbit, a simple evolutionary algorithm is presented. The algorithm uses individuals corresponding to the ternary connection parameters and one zero element is inserted into each individual. Each individual is evaluated by two feature quantities that characterize the stability of the periodic orbit. The zero-insertion is able to reinforce the stability and is convenient to reduce power consumption in a hardware. Applying the algorithm to a class of periodic orbits, the stabilization capability is investigated. Some of the periodic orbits are applicable to control signals of switching power converters.

A Cascade System of Dynamic Binary Neural Networks and Learning of Periodic Orbit

A Cascade System of Dynamic Binary Neural Networks and Learning of Periodic Orbit

Sparsification and Stability of Simple Dynamic Binary Neural Networks

Sparsification and Stability of Simple Dynamic Binary Neural Networks

Learning of Simple Dynamic Binary Neural Networks

Learning of Simple Dynamic Binary Neural Networks