Why are humans slow at math while being great at image processing?

Compared to computers, humans are definitely slower in mathematics, but humans can usually recognise images effortlessly, unlike computers (it takes computers huge hardware and lots of images to train them to recognise simple digits, unlike humans, for example).

Contrary to popular belief, human brain does not behave like a computer. Brain consists of massive interconnected network of neurons. This is how a brain would look like:

Computer on the other hand consists of a series of chips which can mainly do digital calculations. The inside of a processing unit in a computer would look something like:

Brain acts more like an analog super computer (all inter connections and signals are all analog). Whereas computers are purely digital in nature. They convert even analog/continuous variables into digital equivalents for processing. As a result computers are better at processing discrete information like arithmetic. Brain on the other hand can handle massive amount of connected analogous data like speech, visions/video etc. at the same time language, mathematics, advanced logic are all tougher for brains (human or otherwise) to process.

PS: Although artificial neural networks have started by emulating neural networks in the brain, they are no where near how brain actually works.

Originally poster on Quora here: https://www.quora.com/Why-are-humans-slow-at-math-while-being-great-at-image-processing/answer/Gopi-Suvanam

要查看或添加评论,请登录

Gopi Krishna Suvanam的更多文章

  • The Hidden Risks of Over-investment in AI Infrastructure

    The Hidden Risks of Over-investment in AI Infrastructure

    The $500 billion investment in AI Infra definitely looks exciting. But.

    2 条评论
  • The Good, the Bad and the Ugly of ChatGPT

    The Good, the Bad and the Ugly of ChatGPT

    To the uninitiated, ChatGPT is the viral product of the organization OpenAI. It is an AI base chat-bot that interacts…

    2 条评论
  • Transfer Learning: The Future of AI

    Transfer Learning: The Future of AI

    End to end learning is paradigm in machine learning where an algorithm takes inputs and desired actions, to learn a…

    2 条评论
  • Limitations of End-to-End Learning

    Limitations of End-to-End Learning

    (Originally posted as an answer to a Quora question here: https://www.quora.

    1 条评论
  • Value per person is more important

    Value per person is more important

    There has been a mad rush to become the next big thing from eCommerce to social media to SaaS. In this rush, startups…

    1 条评论
  • Neat Learning vs Deep Learning

    Neat Learning vs Deep Learning

    AI world used to have two camps: neats and scruffies. The neats wanted AI solutions to be, well, 'neat'.

    1 条评论
  • Online Learning (by Machines)

    Online Learning (by Machines)

    Most ML methods are applied in a batch process mode. So for example in a simple ML model let’s say we want to learn…

  • Primitives for AI

    Primitives for AI

    I want to explore more structural thoughts in this article. Let’s say I want to build a financial market prediction…

    2 条评论
  • Machine Learning on Small Datasets

    Machine Learning on Small Datasets

    You may be wondering what the image above the title has to do with machine learning. We will get there by the end of…

    4 条评论
  • Can financial markets be predicted? - Brief note for beginners

    Can financial markets be predicted? - Brief note for beginners

    There are lot of concepts at play here. Let me highlight a few.

社区洞察

其他会员也浏览了