Things are getting interesting. The book is only about 90 pages long.
But in summary, it becoming possible to make programs that are both bug free, and can cover a problem domain that cannot be feasibly solved with simple manual programming.
https://www.amazon.com/Neurosymbolic-Programming-Foundations-Trends-Languages/dp/1680839349
It is more advanced. Yes. Very, more so than regular programs in a lot of ways.
It is a concept that comes out of the formal methods community. A more descriptive title is more like "automated program synthesis via mathematical logic and deep learning".
@jmw150 I may actually use this for my thesis if I can grok it, thank you so much for posting it!! 😄
@johnabs @jmw150
I'm sorry- but I can't see myself spending $60USD for a 90 page book :/
maybe $20 at most... I've been ripped off enough by IEEE to know better than to pay more for what I already somewhat read somewhere else in some other fashion.
Now if this was a detailed reference manual- then I can justify it more to myself.
@lucifargundam @jmw150 Check zlib to see if it's there? (And if so, link me xD)
This looks like it is the same book.
https://www.cs.utexas.edu/~swarat/pubs/PGL-049-Plain.pdf
Possible free access through univerities
https://ieeexplore.ieee.org/document/9646874
@jmw150 @lucifargundam Thank you for coming in clutch on this one 😭 I was struggling to find it elsewhere xD
@jmw150 How similar is this to a genetic programming approach? Are they leveraging neural networks? If so, how transparent are the resultant programs to analysis?