Neuro-Symbolic AI - combining Deep Learning with Symbolic Logic for common-sense understanding

Neuro-Symbolic AI - combining Deep Learning with Symbolic Logic for common-sense understanding

I recently read an article in MIT Technology Review entitled "A hybrid AI model lets it reason about the world’s physics like a child". In it, a so-called "Neuro-Symbolic model" is presented, a new AI approach that combines both Deep Learning and Symbolic Logic.

"it uses a neural network to recognize the colors, shapes, and materials of the objects and a symbolic system to understand the physics of their movements and the causal relationships between them. It outperformed existing models across all categories of questions."

The motivation behind this approach was two-fold:

  1. Deep Learning is superb at pattern matching, but bad at actually understanding the data it processes.
  2. Symbolic Logic can capture and model really well human reasoning, correlations and interdependencies between actions, events, objects, people, and "common sense" or even objective rigorous Physics understanding.

Thus, the natural next step is to combine both and leverage the strengths of each in a Hybrid model:

"Deep Learning excels at scalability and pattern recognition; symbolic systems are better at abstraction and reasoning."

Funnily enough that was the approach I took myself for my PhD research back in 1993-96, when I conceived of a Hybrid architecture for automatic Text Summarisation that uses Artificial Neural Networks (ANNs - which have more recently turned into Deep Learning) and Symbolic Reasoning. It was a very ambitious undertaking, but it seemed to be to be the next natural step in AI methodologies. The title of my PhD was "COSY-MATS: A Hybrid Connectionist-Symbolic Approach To The Pragmatic Analysis Of Texts For Their Automatic Summarisation" (University of Manchester, UK, 1996) and you can find the whole Thesis here.

No alt text provided for this image

#NLP #NLU #Summarisation #Summarization #AI #ML #MachineLearning #DeepLearning #SymbolicAI #Logic #Hybrid #Connectionist #NeuroSymbolic #AImodels #CosyMats #ConnectionistSymbolic #ANNs #NeuralNetworks #Manchester

Bob Morgen

Expert in Residence Imperial Enterprise Lab -- Imperial College London

4 年

I have been interested in this hybrid approach as well, particularly for live chat automation. But the difficulty of keeping the Symbolic portion up to date is still with us. My thought is to use the Symbolic portion purely for adding new business rules, ad hoc, until the connectionist data is sufficient for retraining to incorporate those new rules implicitly.

Jonathan Eisenzopf

Chief Strategy and Research Officer at Talkmap

4 年

It’s interesting to see symbolic approaches seing back into vogue as a potential way to fill the gap for statistical models. It makes sense, though it seems like a tricky proposition that will take a lot of experimentation to find a good approach. Thanks for writing a summary of this article.

Ahmed Bouzid

Helping senior living communities leverage cutting edge technology safely and cost effectively.

4 年

Thank you for summarizing and sharing. We should all do more of this.

要查看或添加评论,请登录

Dr Maria Aretoulaki的更多文章

  • You can't trust or fear AI, you should parent it!

    You can't trust or fear AI, you should parent it!

    This week I had the huge honour and immense pleasure to be a Keynote Speaker alongside the Director-General for the…

    3 条评论
  • Life lessons from a Woman in Tech

    Life lessons from a Woman in Tech

    Recently I was part of the GlobalLogic UK&I & Manchester Digital #DigitalHer #WomenInTechnology #WiT "Accelerating your…

    7 条评论
  • Prompt Engineering: Not just stringing words together

    Prompt Engineering: Not just stringing words together

    The term "Prompt Engineering" has produced a lot of confusion in the context of interacting with ChatGPT, the New Bing,…

    5 条评论
  • How to navigate Generative AI in your personal & professional lives

    How to navigate Generative AI in your personal & professional lives

    Skeptical, Yet Optimistic My conversation with Method's Andy Busam on his new "Mediated World" podcast is just out and…

  • A Summary of the State of AI in 2023

    A Summary of the State of AI in 2023

    If you only have 18mins of your life to spare, listen to this The Wall Street Journal podcast with Gerd Gigerenzer for…

  • Are all Voice Assistants doomed?

    Are all Voice Assistants doomed?

    I just read an Arstechnica article lamenting the failure of Amazon Alexa to catch on and how by keeping losing money…

    4 条评论
  • Why AI won't take YOUR job

    Why AI won't take YOUR job

    I recently watched Advantageous on Netflix. A dystopian film about the future of humanity and particularly the bleak…

  • #DigitalHer "Gender Parity in Tech" Roundtable

    #DigitalHer "Gender Parity in Tech" Roundtable

    This morning Manchester Digital and GlobalLogic UK&I hosted a #DigitalHer Breakfast & Roundtable on "Gender Parity in…

    5 条评论
  • The Future of AI-powered Customer Solutions: Making Voicebots & Chatbots great again!

    The Future of AI-powered Customer Solutions: Making Voicebots & Chatbots great again!

    On 29th September I gave an invited talk at the Manchester Digital Emerging Technology Forum - The future of AI-powered…

    2 条评论
  • GPT-3 vs Humans

    GPT-3 vs Humans

    I just read this insightful, albeit controversial for many, article on OpenAI's GPT-3 and Large Language Models and…

    2 条评论

社区洞察

其他会员也浏览了