2.7 KiB
Artificial Intelligence
-
📜 Analysis of Three Bayesian Network Inference Algorithms: Variable Elimination, Likelihood Weighting, and Gibbs Sampling by Rose F. Liu, Rusmin Soetjipto
-
📜 Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search
-
Computing Machinery and Intelligence by A.M. Turing
-
Judea Pearl folder - Papers by Judea Pearl, 2011 winner of the ACM Turing Award.
-
Mastering the Game of Go with Deep Neural Networks and Tree Search by Silver et al.
-
A Universal Music Translation Network (2018) by Noam Mor, Lior Wolf, Adam Polyak & Yaniv Taigman
This paper proposes a method for translating music across musical instruments, genres, and styles. It is based on a multi-domain wavenet autoencoder, with a shared encoder and a disentangled latent space that is trained end-to-end on waveforms. Employing a diverse training dataset and large net capacity, the domain-independent encoder enables translation even from musical domains that were not seen during training. The method is unsupervised and does not rely on supervision in the form of matched samples between domains or musical transcriptions. This method is evaluated on NSynth, as well as on a dataset collected from professional musicians, and achieve convincing translations, even when translating from whistling, potentially enabling the creation of instrumental music by untrained humans.
-
Attention is all you need by Ashish Vaswani et al.
-
ReAct: Synergizing Reasoning and Acting in Language Models (2023) by Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao
While large language models (LLMs) have demonstrated impressive performance across various NLP tasks, their abilities in reasoning (e.g. chain-of-thought prompting) and acting (e.g. action plan generation) have primarily been studied as separate topics. In this paper, we explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner, allowing for greater synergy between the two: reasoning traces help the model induce, track, and update action plans as well as handle exceptions, while actions allow it to interface with external sources to gather additional information.