Рет қаралды 293
Marius and Leo gives us a breakdown of what the key features are in SymbolicAI and their key design considerations.
Part 2 here: studio.kzbin.infoJYip...
It's open source, so do check out their repositories:
Paper - arxiv.org/abs/2402.00854
SymbolicAI - github.com/ExtensityAI/symbol...
SymbolicAI Benchmark - github.com/ExtensityAI/benchmark
~~~
0:00 Introduction
5:45 SymbolicAI vs LangChain
9:06 Why call it SymbolicAI when Symbols are more flexible than traditional symbols
13:10 Domain-specific context: How to match similar Symbols
17:44 Neurosymbolic Pipeline
37:50 Symbol for multi-modal representations
45:20 Expressions: Building upon Symbols to process an instruction
47:03 Flexible Symbol Interpreter
52:35 Operators and Methods
1:02:50 Self-Referential / Hierarchical Structures
1:06:57 Self-Learning by Memory
1:24:28 Why Open Source SymbolicAI?
1:29:40 Teaser for SymbolicAI Evaluations and Conclusion
~~~
AI and ML enthusiast. Likes to think about the essences behind breakthroughs of AI and explain it in a simple and relatable way. Also, I am an avid game creator.
Discord: / discord
LinkedIn: / chong-min-tan-94652288
Online AI blog: delvingintotech.wordpress.com/
Twitter: / johntanchongmin
Try out my games here: simmer.io/@chongmin