Artificial Intelligence

2205 Submissions

[2] viXra:2205.0131 [pdf] submitted on 2022-05-25 03:41:12

Astdp: a More Biologically Plausible Learning

Authors: Shiyuan Li
Comments: 17 Pages.

Spike-timing dependent plasticity in biological neural networks has been proven to be important during biological learning process. On the other hand, artificial neural networks use a different way to learn, such as Back-Propagation or Contrastive Hebbian Learning. In this work we introduce approximate STDP, a new neural networks learning framework more similar to the biological learning process. It uses only STDP rules for supervised and unsupervised learning, every neuron distributed learn patterns and don't need a global loss or other supervised information. We also use a numerical way to approximate the derivatives of each neuron in order to better use SDTP learning and use the derivatives to set a target for neurons to accelerate training and testing process. The framework can make predictions or generate patterns in one model without additional configuration. Finally, we verified our framework on MNIST dataset for classification and generation tasks.
Category: Artificial Intelligence

[1] viXra:2205.0013 [pdf] submitted on 2022-05-02 20:14:08

Implementing Blockchain Technology in Supply Chain Management

Authors: Atul Anand, A. Seetharaman, K. Maddulety
Comments: 14 Pages. Conference: 3rd International Conference on Data Mining and Machine Learning (DMML 2022)

This paper is aimed at studying the factors influencing the implementation of blockchain in supply chain management to solve the current issues faced in the supply chain ecosystem. Supply chains are part and parcel of every business and have multiple inefficiencies in the system. Some of these inefficiencies can be managed by usage of blockchain Platform .Technology, intracompany synergies, intercompany collaboration, extrinsic factors, and innovation are critically evaluated for adoption of blockchain in supply chain. A pilot study is conducted in form survey for analysis of these factors. Hypotheses are derived for these factors for quantitative research. Subsequently these hypotheses are examined with the help of ADANCO2.3 for structural equation modelling. As an outcome, it is evident that Innovation and Extrinsic factors are significantly impacting the adoption of blockchain in supply chain management.
Category: Artificial Intelligence