Artificial Intelligence, Consciousness, Hyperdimensional Computing: Introduction

03 August 2023

MAIB: Manifold learning, Artificial Intelligence, Biology Forum (MAIB)

  • Momiao Xiong, Ph. D, Professor in Department of Biostatistics snd Data Science , University of Texas, School of Public Health. Dr. Xiong graduated from the Department of Statistics at the University of Georgia in 1993. From 1993 to 1995, Dr. Xiong was postdoctoral fellow at the University of Southern California working with Michael Waterman.

  • Research Interest： Causal Inference, Artificial Intelligence, Hiperdimensional Computing, Statistic Genetics and Bioinformatics .

Intelligence is the ability to perceive information and to retain it as knowledge to be applied towards adaptive behavior within a changing environment.Many applications run machine learning algorithms to perform cognitive tasks.The learning algorithms have been shown effectiveness for many tasks, e.g., object tracking , speech recognition , image classification , etc. However, the high computational complexity and memory requirement of existing deep learning algorithms hinder usability to a wide variety of real-life embedded applications where the device resources and power budget is limited. Redesign the algorithms themselves using strategies that more closely model the ultimate efficient learning machine: the human brain. Hyperdimensional computing (HDC) is one such strategy developed by interdisciplinary research.It is based on a short-term human memory model, Sparse distributed memory, emerged from theoretical neuroscience . HDC is motivated by the understanding that the human brain operates on highdimensional representations of data originating from the large size of brain circuits.

工智能，人工意识和超维向量计算课程简介:

现在的数字计算机是冯诺依曼计算机。但目前的数字计算机发展遭遇到如下瓶颈。（1）耗能大，（2）有毒的废料，（3）小型化的物理，技术和经济方面的限制和（4）日益增长软件系统和算法的复杂性。为了克服这些困难，目前广泛流行的非数字计算是神经形态计算，也就是人脑鼓午下的省能，高效，並行计算和新型微芯片。量子计算机也在异军突起。目前的人工智能计算缺乏有效的算法包括符号运算，计划，推理，情感，行为和意识。和冯。诺意曼计算同时发展起来的是统计计算模型，即数据，模型，参数估计，通过训练来迭代估计参数，通过模型来预测结果。统计计算是一种多阶段的计算。现在的大语言模型和其他一些主流的人工智能算法就是基于统计模型的。而大恼鼓午下的神经形态计算或超维向量计算就是利用超维向量一次性地计算结果，不需要模型或迭代。所以也称为one pass 计算。这是一个完全与我们以前计算不同的范式。超维向量计算具有能耗低，计算速度快，成本低，稳健性，抗干扰能力強等优点。本课程介绍的人工智能和超维计算包括存储计算，超维符号，整数，实数和实函数的编码理论，分类，回归，语言处理，图象，视频，多模态，机器人，自动驾驶以及他们运用在生物中的DNA，基因表达，蛋白质，甲基化，代谢，单细胞的组合数据，空间数据综合分析，因果分析，因果网络，药物的开发和评估，穿戴设备计算，情感计算，人工意识计算以及人工智能和人工意识的相互作用和结合。以期建立一条通往一般人工智能的道路。计算的结构以前过分地强调了集中的云计算，而没有把云计算和边缘计算紧密结合起来，形成集中与分散相结合的云-边缘计算体系。超维向量计算的一个致命缺点是缺乏系统的生成式人工智能理论。我们希望随着本课程的进展，生成式人工智能的超维向量算法能初步地建立超来。本课程以洪水预测和气象分析，智能医院和公共卫生作为两个案例来讨论云一边缘计算体系设计的原则。本课程将会适当佈置家庭作业和小的项目。

•

blog comments powered by Disqus