当前位置: X-MOL 学术Front. Comput. Neurosci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Understanding the Impact of Neural Variation and Random Connections on Inference
Frontiers in Computational Neuroscience ( IF 2.1 ) Pub Date : 2021-04-19 , DOI: 10.3389/fncom.2021.612937
Yuan Zeng 1 , Zubayer Ibne Ferdous 1 , Weixiang Zhang 2 , Mufan Xu 2 , Anlan Yu 1 , Drew Patel 1 , Valentin Post 1 , Xiaochen Guo 1 , Yevgeny Berdichevsky 1, 3 , Zhiyuan Yan 1
Affiliation  

Recent research suggests that in vitro neural networks created from dissociated neurons may be used for computing and performing machine learning tasks. To develop a better artificial intelligent system, a hybrid bio-silicon computer is worth exploring. However, the performance of current hybrid bio-silicon design is still far from the silicon-based computer. One reason may be that the living neural network has many intrinsic properties, such as the random network connectivity, high network sparsity, and large neural and synaptic variability. These properties may lead to new design considerations and existing algorithms may need to be adjusted for living neural network implementation. This work investigates the impact of neural variation and random connections on the inference of learning algorithms. A two-layer hybrid bio-silicon platform is constructed and a three-stage design method is proposed for fast development of living neural network algorithms. Neural variation and dynamics are verified by fitting model parameters with biological experimental results. Random connections are generated under different connection probabilities to vary network sparsity. A multi-layer perceptron algorithm is tested with biological constraints on the MNIST dataset. The results show that a reasonable inference accuracy can be achieved when neural variations and random network connections are taken into account. A new adaptive pre-processing technique is proposed to ensure good learning accuracy with different living neural network sparsity.

中文翻译:

了解神经变异和随机连接对推理的影响

最近的研究表明,由解离的神经元创建的体外神经网络可用于计算和执行机器学习任务。为了开发更好的人工智能系统,混合生物硅计算机值得探索。但是,当前的混合生物硅设计的性能仍然远远不及基于硅的计算机。原因之一可能是活神经网络具有许多固有属性,例如随机网络连接性,较高的网络稀疏性以及较大的神经和突触变异性。这些属性可能导致新的设计考虑,并且可能需要调整现有算法以实现实时神经网络。这项工作研究了神经变异和随机连接对学习算法推理的影响。构建了两层混合式生物硅平台,并提出了一种三阶段设计方法,以快速开发实时神经网络算法。通过将模型参数与生物学实验结果拟合来验证神经变异和动力学。随机连接是根据不同的连接概率生成的,以改变网络稀疏性。在MNIST数据集上使用生物学约束测试了多层感知器算法。结果表明,在考虑神经变异和随机网络连接的情况下,可以获得合理的推理精度。提出了一种新的自适应预处理技术,以确保在不同的生命神经网络稀疏性下获得良好的学习准确性。通过将模型参数与生物学实验结果拟合来验证神经变异和动力学。随机连接是根据不同的连接概率生成的,以改变网络稀疏性。在MNIST数据集上使用生物学约束测试了多层感知器算法。结果表明,在考虑神经变异和随机网络连接的情况下,可以获得合理的推理精度。提出了一种新的自适应预处理技术,以确保在不同的生命神经网络稀疏性下获得良好的学习准确性。通过将模型参数与生物学实验结果拟合来验证神经变异和动力学。随机连接是根据不同的连接概率生成的,以改变网络稀疏性。在MNIST数据集上使用生物学约束测试了多层感知器算法。结果表明,在考虑神经变异和随机网络连接的情况下,可以获得合理的推理精度。提出了一种新的自适应预处理技术,以确保在不同的生命神经网络稀疏性下获得良好的学习准确性。在MNIST数据集上使用生物学约束测试了多层感知器算法。结果表明,在考虑神经变异和随机网络连接的情况下,可以获得合理的推理精度。提出了一种新的自适应预处理技术,以确保在不同的生命神经网络稀疏性下获得良好的学习准确性。在MNIST数据集上使用生物学约束测试了多层感知器算法。结果表明,在考虑神经变异和随机网络连接的情况下,可以获得合理的推理精度。提出了一种新的自适应预处理技术,以确保在不同的生命神经网络稀疏性下获得良好的学习准确性。
更新日期:2021-04-19
down
wechat
bug