[HTML][HTML] Human evaluation of automatically generated text: Current trends and best practice guidelines
Currently, there is little agreement as to how Natural Language Generation (NLG) systems
should be evaluated, with a particularly high degree of variation in the way that human …
should be evaluated, with a particularly high degree of variation in the way that human …
A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning
E Brochu, VM Cora, N De Freitas - arXiv preprint arXiv:1012.2599, 2010 - arxiv.org
We present a tutorial on Bayesian optimization, a method of finding the maximum of
expensive cost functions. Bayesian optimization employs the Bayesian technique of setting …
expensive cost functions. Bayesian optimization employs the Bayesian technique of setting …
Generative agents: Interactive simulacra of human behavior
Believable proxies of human behavior can empower interactive applications ranging from
immersive environments to rehearsal spaces for interpersonal communication to prototyping …
immersive environments to rehearsal spaces for interpersonal communication to prototyping …
Emergent tool use from multi-agent autocurricula
Through multi-agent competition, the simple objective of hide-and-seek, and standard
reinforcement learning algorithms at scale, we find that agents create a self-supervised …
reinforcement learning algorithms at scale, we find that agents create a self-supervised …
A survey and critique of multiagent deep reinforcement learning
Deep reinforcement learning (RL) has achieved outstanding results in recent years. This has
led to a dramatic increase in the number of applications and methods. Recent works have …
led to a dramatic increase in the number of applications and methods. Recent works have …
Extracting medicinal chemistry intuition via preference machine learning
The lead optimization process in drug discovery campaigns is an arduous endeavour where
the input of many medicinal chemists is weighed in order to reach a desired molecular …
the input of many medicinal chemists is weighed in order to reach a desired molecular …
TaleBrush: Sketching stories with generative pretrained language models
While advanced text generation algorithms (eg, GPT-3) have enabled writers to co-create
stories with an AI, guiding the narrative remains a challenge. Existing systems often …
stories with an AI, guiding the narrative remains a challenge. Existing systems often …
Measuring human perceptions of a large-scale urban region using machine learning
Measuring the human sense of place and quantifying the connections among the visual
features of the built environment that impact the human sense of place have long been of …
features of the built environment that impact the human sense of place have long been of …
[图书][B] Mathematics for machine learning
The fundamental mathematical tools needed to understand machine learning include linear
algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability …
algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability …
Findings of the 2017 conference on machine translation (wmt17)
This paper presents the results of the WMT17 shared tasks, which included three machine
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …