Review of advances in neural networks: Neural design technology stack

Almasi, Adela-Diana; Woźniak, Stanisław; Cristea, Valentin; Leblebici, Yusuf; Engbersen, Ton

doi:10.1016/j.neucom.2015.02.092

Cited by 67 publications

(28 citation statements)

References 60 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The activation function used should be non-linear in order to properly model the behavior of biological neurons and to be able to solve non-linear problems [56]. The linear mapping in which the activation is equal to the received signal (A i = f a (S i ) = S i ) is called the identity mapping/function, or the linear activation function.…”

Section: S B W Andmentioning

confidence: 99%

See 1 more Smart Citation

Solving vapor-liquid flash problems using artificial neural networks

Poort

Ramdin

Kranendonk³

et al. 2019

Fluid Phase Equilibria

View full text Add to dashboard Cite

Vapor-liquid phase equilibrium (flash) calculations largely contribute to the total computation time of many process simulation models. As a result, process simulations, especially dynamic cases, are limited in the amount of detail that can be included due to time restrictions. In addition, under certain conditions flash calculations can fail to provide acceptable results. In this work, artificial neural networks were investigated as a potentially faster and more robust alternative to conventional flash calculation methods. Classification neural networks were used to determine the phase stability of a given mixture of fluids, while regression networks were used to make predictions of thermodynamic property values. In addition to conventional flash types such as the constant pressure, constant temperature (P T ), and constant pressure, constant entropy (P S) flash, neural networks are used to develop two concept flash types: a constant entropy, constant volume (SV ), and a constant enthalpy, constant volume (HV ) flash. All neural networks were trained on, and compared to, data generated using the P T -flash algorithm from the Thermodynamics for Engineering Applications (TEA) property calculator. Data was generated for mixtures of water and methanol over a wide range of pressures and temperatures. The artificial neural networks showed speed improvements over TEA of up to 35 times for phase classification and 15 times for property predictions. Overall phase classification accuracy scores of around 97% were achieved. Average property value prediction errors range between 0.5% and 7% when compared to the spread in magnitude of the test data, and R 2 scores were in the general order of 0.95 and higher, although classification and property prediction in the two-phase region showed markedly higher errors than properties in the pure liquid or vapor regions. Moreover, thermodynamic consistency and the stability of a system consisting of multiple neural network flash types both still require considerable improvement. Finally, this work shows that artificial neural networks can be used to create unconventional flash types such a the SV -and HV -flash.i

show abstract

Section: S B W Andmentioning

confidence: 99%

“…A neural network is trained in a data-driven manner, meaning that it learns by example from a (preferably large) set of predetermined data instances [9,56]. The data set contains many instances of inputs with a known corresponding output, i.e.…”

Section: The Basic Concept Of Trainingmentioning

confidence: 99%

Solving vapor-liquid flash problems using artificial neural networks

Poort

Ramdin

Kranendonk³

et al. 2019

Fluid Phase Equilibria

View full text Add to dashboard Cite

show abstract

“…Table compares the various biological neural networks, SNNs, and ANNs on synapse models, neuron models, network topology, learning algorithms, implementation, applications, and other features . Since ANNs and SNNs simulate different characteristics of the biological neural networks, ANNs based deep neural networks (DNNs) and SNNs based learning systems are both being developed continuously for different purposes . Currently, implementations of neural networks are mostly based on the von Neumann computing system (VCS) such as CPU, GPU, and their cluster, which is powerful for logical computing but not efficient for neuronal and synaptic computing .…”

Section: Introductionmentioning

confidence: 99%

Neuromorphic Computing with Memristor Crossbar

Zhang

Huang

et al. 2018

Physica Status Solidi (a)

View full text Add to dashboard Cite

Neural networks, one of the key artificial intelligence technologies today, have the computational power and learning ability similar to the brain. However, implementation of neural networks based on the CMOS von Neumann computing systems suffers from the communication bottleneck restricted by the bus bandwidth and memory wall resulting from CMOS downscaling. Consequently, applications based on large-scale neural networks are energy/ area hungry and neuromorphic computing systems are proposed for efficient implementation of neural networks. Neuromorphic computing system consists of the synaptic device, neuronal circuit, and neuromorphic architecture. With the two-terminal nonvolatile nanoscale memristor as the synaptic device and crossbar as parallel architecture, memristor crossbars are proposed as a promising candidate for neuromorphic computing. Herein, neuromorphic computing systems with memristor crossbars are reviewed. The feasibility and applicability of memristor crossbars based neuromorphic computing for the implementation of artificial neural networks and spiking neural networks are discussed and the prospects and challenges are also described.

show abstract

“…The key contributions with respect to existing neuromorphic design methods [5], [14], [15] are threefold. First, the equivalence (from a geometric, dynamical systems, and input-output perspective) of the designed circuit and high-dimensional biophysical neuron models close to the transition between distinct spiking modes is a provable consequence of the used approach.…”

Section: Introductionmentioning

confidence: 99%

Implementing robust neuromodulation in neuromorphic circuits

Castaños

Franci

2017

Neurocomputing

View full text Add to dashboard Cite

Abstract-We introduce a methodology to implement the physiological transition between distinct neuronal spiking modes in electronic circuits composed of resistors, capacitors and transistors. The result is a simple neuromorphic device organized by the same geometry and exhibiting the same input-output properties as high-dimensional electrophysiological neuron models. Preliminary experimental results highlight the robustness of the approach in real-world applications.

show abstract

Review of advances in neural networks: Neural design technology stack

Cited by 67 publications

References 60 publications

Solving vapor-liquid flash problems using artificial neural networks

Solving vapor-liquid flash problems using artificial neural networks

Neuromorphic Computing with Memristor Crossbar

Implementing robust neuromodulation in neuromorphic circuits

Contact Info

Product

Resources

About