This paper has been studied in Quantum Learning Vector Quantization Neural Network. The concept of competition and model of competitive network has been studied. It analyses model of Quantum Learning Vector Quantization Neural Network and LVQ algorithm. Quantum Learning Vector Quantization Neural Network is a hybrid neural network and quantum computing theory is used in the Quantum Learning Vector Quantization Neural Network directly to build Quantum Learning Vector Quantization Neural Network. Model of Quantum Learning Vector Quantization Neural Network and Quantum-LVQ algorithms are proposed. In the study of clustering problem, experiments show that Quantum Learning Vector Quantization Neural Network have an advantage over than Learning Vector Quantization Neural Network.This paper has been studied in Quantum Learning Vector Quantization Neural Network. The concept of competition and model of competitive network has been studied. It analyses model of Quantum Learning Vector Quantization Neural Network and LVQ algorithm. Quantum Learning Vector Quantization Neural Network is a hybrid neural network and quantum computing theory is used in the Quantum Learning Vector Quantization Neural Network directly to build Quantum Learning Vector Quantization Neural Network. Model of Quantum Learning Vector Quantization Neural Network and Quantum-LVQ algorithms are proposed. In the study of clustering problem, experiments show that Quantum Learning Vector Quantization Neural Network have an advantage over than Learning Vector Quantization Neural Network.

Electronic and Mechanical Engineering and Information TechnologyAug 1, 201114 citations

A Quantization-Model of the Neural Nets

Matthias Reuter

Lecture notes in computer scienceJan 1, 19992 citations

Iteration-Aware Dynamic Quantization Neural Belief Propagation Decoder

Liangsi Ma, Bei Liu, Xin Su

For some linear codes, neural networks have been found to be a way to enhance traditional belief propagation (BP) decoder. When deploying such methods in practice, quantization issues also need to be considered. Considering that the messages of variable/check nodes are variable during the BP decoding process, this paper proposes a dynamic quantization method to predict the optimal bit-width for the node’s message quantization in different decoding iterations. We build a shallow neural network as a bit-width predictor and train it jointly with a neural belief propagation decoding network. During actual decoding, the bit prediction network will generate appropriate bit-width for quantizing the messages of each layer of nodes. Finally, simulation experiments validate the effectiveness of the proposed quantization method.For some linear codes, neural networks have been found to be a way to enhance traditional belief propagation (BP) decoder. When deploying such methods in practice, quantization issues also need to be considered. Considering that the messages of variable/check nodes are variable during the BP decoding process, this paper proposes a dynamic quantization method to predict the optimal bit-width for the node’s message quantization in different decoding iterations. We build a shallow neural network as a bit-width predictor and train it jointly with a neural belief propagation decoding network. During actual decoding, the bit prediction network will generate appropriate bit-width for quantizing the messages of each layer of nodes. Finally, simulation experiments validate the effectiveness of the proposed quantization method.

World Conference on Computing and Communication Technologies (WCCCT)Apr 12, 20240 citations

The Quantum-like Behavior of Neural Networks

Thomas Filk A

The frontiers collectionJan 1, 20222 citations

Stochastic Quantization

Springer eBooksAug 3, 20070 citations

The Wavefunction of Continuous-Time Recurrent Neural Networks

Ikjyot Singh Kohli, Michael C. Haslam

In this paper, we explore the possibility of deriving a quantum wavefunction for continuous-time recurrent neural network (CTRNN). We did this by first starting with a two-dimensional dynamical system that describes the classical dynamics of a continuous-time recurrent neural network, and then deriving a Hamiltonian. After this, we quantized this Hamiltonian on a Hilbert space $\mathbb{H} = L^2(\mathbb{R})$ using Weyl quantization. We then solved the Schrodinger equation which gave us the wavefunction in terms of Kummer's confluent hypergeometric function corresponding to the neural network structure. Upon applying spatial boundary conditions at infinity, we were able to derive conditions/restrictions on the weights and hyperparameters of the neural network, which could potentially give insights on the the nature of finding optimal weights of said neural networks.In this paper, we explore the possibility of deriving a quantum wavefunction for continuous-time recurrent neural network (CTRNN). We did this by first starting with a two-dimensional dynamical system that describes the classical dynamics of a continuous-time recurrent neural network, and then deriving a Hamiltonian. After this, we quantized this Hamiltonian on a Hilbert space $\mathbb{H} = L^2(\mathbb{R})$ using Weyl quantization. We then solved the Schrodinger equation which gave us the wavefunction in terms of Kummer's confluent hypergeometric function corresponding to the neural network structure. Upon applying spatial boundary conditions at infinity, we were able to derive conditions/restrictions on the weights and hyperparameters of the neural network, which could potentially give insights on the the nature of finding optimal weights of said neural networks.

arXiv:2102.09399Feb 13, 20210 citations

\mathbb{H} = L^2(\mathbb{R})

using Weyl quantization. We then solved the Schrodinger equation which gave us the wavefunction in terms of Kummer's confluent hypergeometric function corresponding to the neural network structure. Upon applying spatial boundary conditions at infinity, we were able to derive conditions/restrictions on the weights and hyperparameters of the neural network, which could potentially give insights on the the nature of finding optimal weights of said neural networks.