🔗 Sharma, B. Lungsi., & Wells, R. B. (2017, October 23-25). The Mathematical Order Structure of Subjective Time. 1st Annual Conference of the Timing Research Forum, Strasbourg, France. 🔗

As one interacts with the environment, the order of perception of objects and events are important. When you confront an object it’s the knowledge that materializes. The knowledge that there is a pen, a paper and a desk in front of you is discovered instantly. Damasio (1999) hypothesizes that each materialized knowledge is the content of each pulse-like generation of consciousness. Studies suggests neural synchrony to play a role in temporal processing and consciousness (Meck et al., 2014). We may therefore look at temporal processing as that which engenders a sense of self in the act of knowing (an inner sense). The logical or mathematical view of the role of subjective time or time processing is hence the process of order structuring, the property that mathematicians refer to as weak and strict partial order defined by reflexive, irreflexive, antisymmetric and transitive properties. The next perception grows out of the previous moment and so on … resulting in a timeline view of the chain. This is strict partial ordering. But this has the shortcoming that a moment in time is not relatable to itself. It has irreflexive property. A timeline view is therefore not sufficient to represent the time process. Partial ordering with the reflexive property is called weak partial ordering. This extends the onedimensional timeline into a multi-dimensional timescape. The parts of the timescape represents markings of perceptions at moments in time. These are like Damasio’s pulses of consciousness. The order structure is a system of self-regulatory transformations. A direct relationship of mental structures and mathematical structures was discovered by Piaget and Dieudonne (Piaget, 1970). This paper will present a mathematical description of “what time does for perception?” (October 23, 2017)

🔗 Sharma, B. Lungsi. (2013). A Minimal ART network for comparation. Moscow, U.S.A: University of Idaho. 🔗

Entry needed. (December 20, 2013)

🔗 Gotshall, S., Canine, B., Jennings, B., & Soule, T. (2005, July 31 - August 4). Evolutionary training of a biologically realistic spino-neuromuscular system. Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005., Montreal, Que., 2005, pp. 616-621 vol. 1, doi: 10.1109/IJCNN.2005.1555843. 🔗

This paper presents a biologically realistic model of the spino-neuromuscular system (SNMS). The model uses a pulse-coded recurrent neural network to control a simulated humanlike arm. We use a genetic algorithm to train the network based on a target behaviour for the arm. Our goal is to create a useful model for studying the function and behaviour of neural pathways in the SNMS. The genetic algorithm is able to train the network to actuate the arm to achieve controlled motion. Our experimental results demonstrate that certain types of feedback pathways are important for controlling certain movements. (July 31 - August 4, 2005)

🔗 Wells, R. B., Bhattacharya, A., Sharon, B., Gupta, P., Young, S., Giri, S., Terseer, I., & Cox, D. (2005, July 31 - August 4). Forgetful logic circuits for pulse-mode neural networks. Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005., Montreal, Que., 2005, pp. 616-621 vol. 1, doi: 10.1109/IJCNN.2005.1555902. 🔗

We introduce a new class of pulse-mode circuit, called forgetful logic. Forgetful logic circuits can be used to implement more complex waveform signaling in pulse-mode artificial neural network circuits. The basic operation of forgetful logic is first explained. Its application is then illustrated by numerous examples. (July 31 - August 4, 2005)

🔗 Sharon, B., & Wells, R. B. (2004). VLSI implementation of neuromime pulse generator for Eckhorn neurons. Electronics Letters, vol. 40, no. 18, pp. 1143-1144, doi: 10.1049/el:20045701. 🔗

The Eckhorn neuron model has important applications in image processing by means of pulse-coded neural networks. It is composed of two principal parts, the dendrite and the neuromime pulse generator. The authors discuss a VLSI design of a neuromime pulse generator for implementation in Eckhorn neurons. (September 2, 2004)

🔗 Barnes, B. C., & Wells, R. B. (2003, November 2-6). A versatile pulse-mode biomimic artificial neuron using a capacitor-free integrate-and-fire technique. IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468), Roanoke, VA, USA, 2003, pp. 2968-2972 Vol.3, doi: 10.1109/IECON.2003.1280720. 🔗

A biomimic artificial neuron design with Schmitt trigger action potential pulsed outputs, independent excitatory and inhibitory pulsed inputs, and modulatory pulse width control is presented. The neuron is suitable for use in pulse-coded neural network applications. (November 2-6, 2003)

🔗 Barnes, B. C., Wells, R. B., & Frenzel, J. F. (2003). PWM characteristics of capacitor-free integrate-and-fire neuron. Electronics Letters, vol. 39, no. 16, pp. 1191-1193, doi: 10.1049/el:20030769. 🔗

An artificial neuron with Schmitt trigger action potential pulsed outputs demonstrating pulsewidth modulation capability is presented. One signal processing application of this capability is the mimicking of neuronal burst phenomena without the need for explicitly generating burst trains of individual pulses. (August 7, 2003)

🔗 Wells, R. B., Vongkunghae, A., & Yi, J. (2002, November 2-6). A signal processing model for laser print engines. IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02, Sevilla, 2002, pp. 1514-1519 vol.2, doi: 10.1109/IECON.2002.1185504. 🔗

An accurate printer model that is efficient enough to be used by halftoning algorithms is proposed. The signal processing model (SPM) proposed in this paper utilizes a physical model to train adaptive linear combiners (ALCs), after which the average exposure of each subpixel for any input pattern can be calculated using the optimized weight vector. The SPM can be used to model multi-level halftoning and resolution enhancement, as well as traditional halftoning. The SPM is comprised of a single layer of ALC's and is adapted using the LMS algorithm. A relatively small number of training patterns suffices to obtain adequate model accuracy. (November 5-8, 2002)

🔗 Wells, R. B., & Barnes, B. (2002). Capacitor-free leaky integrator for biomimic artificial neurons. Electronics Letters, vol. 38, no. 17, pp. 974-976, doi: 10.1049/el:20020679. 🔗

A method for implementing capacitor-free leaky integrators for biomimic artificial neurons is presented. The method employs a low-gain non-inverting amplifier with nonlinear feedback resistors implemented from PMOS devices operating in the triode region. (August 15, 2002)