Which logic programming language relies directly on Horn clauses and First-Order Resolution as its execution mechanism?
PROLOG (Programming in Logic) uses SLD-resolution on Horn clauses to execute queries against a knowledge base of facts and rules.
What distinguishes L1 Regularization (Lasso) from L2 Regularization (Ridge)?
L1 (Lasso) adds lambda * sum(|w_i|), driving less important coefficients to zero, whereas L2 (Ridge) adds lambda * $sum(w_i^2)$, shrinking weights toward zero without setting them exactly to zero.
In classical Sequence-to-Sequence (Seq2Seq) neural machine translation models, what was the primary operational bottleneck of the basic recurrent Encoder-Decoder framework?
Original Seq2Seq architectures had to squeeze the entire semantic meaning of long input sequences into a single fixed-dimensional bottleneck vector, degrading performance on long sentences.
What internal component is maintained by a 'Model-based Reflex Agent' to handle partial observability?
A model-based agent maintains an internal model of the world's dynamics (transition model) and sensor physics (sensor model) to track unobserved aspects.
How does Proof by Refutation (Resolution Refutation) prove that a Knowledge Base KB entails a query sentence alpha?
Resolution refutation asserts KB ^ ~alpha; if this set of clauses is unsatisfiable, resolving complementary literals derives a contradiction (empty clause Box), proving KB entails alpha.