McCulloch–Pitts Neural Network Model

Chakraverty, Snehashish; Sahoo, Deepti Moyi; Mahato, Nisha Rani

doi:10.1007/978-981-13-7430-2_11

Cited by 16 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This neuron takes an aggregate of weighted inputs, applies some function, and gives the output, as shown in Figure 1. For McCulloch Pitt's (MP) neuron model, input/output can only be Boolean and all weights are unity [18]. All the input are added together, since all the inputs are Boolean, which means counting the number of things that have a value of 1.…”

Section: Methodsmentioning

confidence: 99%

Application of Machine Learning in Battery: State of Charge Estimation Using Feed Forward Neural Network for Sodium-Ion Battery

Darbar

Bhattacharya

2022

Electrochem

View full text Add to dashboard Cite

Estimating the accurate State of Charge (SOC) of a battery is important to avoid the over/undercharging and protect the battery pack from low cycle life. Current methods of SOC estimation use complex equations in the Extended Kalman Filter (EKF) and the equivalent circuit model. In this paper, we used a Feed Forward Neural Network (FNN) to estimate the SOC value accurately where battery parameters such as current, voltage, and charge are mapped directly to the SOC value at the output. A FNN could self-learn the weights with each training data point and update the model parameters such as weights and bias using a combination of two gradient descents (Adam). This model comprises the Dropout technique, which can have many neural network architectures by dropping the neuron/mode at each epoch/training cycle using the same weights and biases. Our FNN model was trained with data comprising different current rates and tested for different cycling data, for example, 5th, 10th, 20th, and 50th cycles and at a different cutoff voltage (4.5 V). The battery used for estimating the SOC value was a Na-ion based battery, which is highly non-linear, and it was fabricated in a house using Na0.67Fe0.5Mn0.5O2 (NFM) as a cathode and Na metal as a reference electrode. The FNN successfully estimated the SOC value for the highly non-linear nature of the Na-ion battery at different current rates (0.05 C, 0.1 C, 0.5 C, 1 C, 2 C), for different cycling data, and at higher cut-off voltage of –4.5 V Na+, reaching the R2 value of ~0.97–~0.99, ~0.99, and ~0.98, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Application of Machine Learning in Battery: State of Charge Estimation Using Feed Forward Neural Network for Sodium-Ion Battery

Darbar

Bhattacharya

2022

Electrochem

View full text Add to dashboard Cite

show abstract

“…Modeling the self-organization of neural networks (NNs) dates back many years, with the first demonstration being Fukushima's neocognitron [17,18]. It was built out of simple McCulloch-Pitts neuron units [19], arranged in a hierarchical multi-layer neural network, capable of learning to perform pattern-recognition. Although the weights connecting the different layers were modified via unsupervised learning paradigms, the architecture of the network was hard-coded, which was inspired by Hubel and Wiesels' [20] model of simple and complex cells in the visual cortex.…”

Section: Related Workmentioning

confidence: 99%

Self-organization of multi-layer spiking neural networks

Raghavan¹,

Liu²,

Thomson³

2020

Preprint

View full text Add to dashboard Cite

Living neural networks in our brains autonomously self-organize into large, complex architectures during early development to result in an organized and functional organic computational device. A key mechanism that enables the formation of complex architecture in the developing brain is the emergence of traveling spatiotemporal waves of neuronal activity across the growing brain. Inspired by this strategy, we attempt to efficiently self-organize large neural networks with an arbitrary number of layers into a wide variety of architectures. To achieve this, we propose a modular tool-kit in the form of a dynamical system that can be seamlessly stacked to assemble multi-layer neural networks. The dynamical system encapsulates the dynamics of spiking units, their inter/intra layer interactions as well as the plasticity rules that control the flow of information between layers. The key features of our tool-kit are (1) autonomous spatio-temporal waves across multiple layers triggered by activity in the preceding layer and (2) Spike-timing dependent plasticity (STDP) learning rules that update the inter-layer connectivity based on wave activity in the connecting layers. Our framework leads to the self-organization of a wide variety of architectures, ranging from multi-layer perceptrons to autoencoders. We also demonstrate that emergent waves can self-organize spiking network architecture to perform unsupervised learning, and networks can be coupled with a linear classifier to perform classification on classic image datasets like MNIST. Broadly, our work shows that a dynamical systems framework for learning can be used to self-organize large computational devices.Preprint. Under review.

show abstract

“…In 1943, neural network behavior was analyzed logically. McCulloch and Pitts [14] introduced this idea in the given year to formally describe neural network behavior. J. von Neumann [15] applied McCulloch and Pitts' ideas to digital circuits in 1945, so S. Kleene [16] defines the first finite automaton in the representation of events in nerve nets and finite automata [17].…”

Section: Introductionmentioning

confidence: 99%

The Influence of Temporal Logic on Finite Automata

Kareem¹,

Senjari²

2023

(AREJ)

View full text Add to dashboard Cite

The theory of automata combines ideas from engineering, linguistics, mathematics, philosophy, etc. The Entscheidungsproblem asks if it is possible to design a series of steps that replaces a mathematician. An automaton is an abstract machine that processes data. C. Shannon's theory is today's most popular despite having no relationship with the other. The Kt system is called "minimal" because it makes no assumptions about the structure of time. In LKt, we have four monary temporal operators, F, P, G and H, which are mutually interdefinable. Interdefinability means that we will pass logic in the future is the same as saying I will never fail logic, interpreting not passing logic as failing logic. The minimal system syntax of temporal logic introduces operators that have the property of being defined in terms of others. Modal logic studies the reasoning that involves the use of expressions "necessarily" and "possibly". In this article, we will represent through a finite automaton the temporal logic formula Fp. It allows us to see an acceptance pattern for Fp by considering two variables: p and q. Kt's axiomatic system of time expresses the idea that both the present and the past are fixed, if it has always been in the past that it will be some time in the future that p is now. No philosophical argument supports deterministic time flow; the logic of time must be open.Temporal logic has revived many old problems, from the Megaric-Stoics to the minimal system of temporal logic. Our work suggests that the future operators of system Kt follow an evaluation pattern, but we must be cautious because this pattern can only apply to models whose time flow is based on instants and precedence relations.

show abstract

McCulloch–Pitts Neural Network Model

Cited by 16 publications

References 0 publications

Application of Machine Learning in Battery: State of Charge Estimation Using Feed Forward Neural Network for Sodium-Ion Battery

Application of Machine Learning in Battery: State of Charge Estimation Using Feed Forward Neural Network for Sodium-Ion Battery

Self-organization of multi-layer spiking neural networks

The Influence of Temporal Logic on Finite Automata

Contact Info

Product

Resources

About