Pedro Domingos Proposes Tensor Logic, a Language Unifying Neural and Symbolic AI
pmddomingos · x · 2026-09-05
AI researcher Pedro Domingos released the arXiv paper "Tensor Logic: The Language of AI", touting tensor product representations as "obviously the future of AI" (joking it was invented too soon for Schmidhuber to claim credit).
Key claims:
- PyTorch/TensorFlow are Python add-ons lacking automated reasoning and knowledge acquisition, while LISP/Prolog lack scalability and learning support.
- Tensor Logic unifies neural and symbolic AI with a single construct: the tensor equation — logical rules and Einstein summation are essentially the same operation, and everything else reduces to them.
- The paper shows elegant implementations of transformers, formal reasoning, kernel machines, and graphical models.
- Its most important new direction: sound reasoning in embedding space, combining neural scalability with symbolic reliability and transparency.
More from Research
- ChatGPT 5.6 proves remaining Kozma-Nitzan conjectures in ~10 hours, formalized in ~100K lines of Lean — burny_tech · 2026-09-05
- NextLatent teaches transformers to predict their own latent states, enabling 3.3x faster inference — burny_tech · 2026-09-05
- Prof. Tom Yeh releases interactive diagram comparing Full Fine-Tuning vs LoRA by hand — ProfTomYeh · 2026-09-05
- Paper finds LLM multi-agent systems need only about six distinct communication topologies — omarsar0 · 2026-09-05
- 21 researchers from Stanford, Oxford, DeepMind argue LLMs are a dead end to AGI — GaryMarcus · 2026-09-05
- Burkov recommends Peng Ding's causal inference textbook to fix AI's correlation-only blind spot — burkov · 2026-09-05