{"id":17,"date":"2021-03-31T21:44:10","date_gmt":"2021-04-01T00:44:10","guid":{"rendered":"https:\/\/www.servidores.ufscar.br\/talmeida\/?page_id=17"},"modified":"2026-04-28T15:11:41","modified_gmt":"2026-04-28T18:11:41","slug":"publications","status":"publish","type":"page","link":"https:\/\/www.servidores.ufscar.br\/talmeida\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"\n
\n
\n

Publications<\/h1>\n<\/div><\/div>\n<\/div><\/div>\n\n\n\n
\n
\n
\n

Electronic versions of the published documents (.pdf or .ps) are available upon request.<\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n\n\n\n

<\/div>\n\n\n\n
\n
<\/div>\n\n\n\n

Highlights<\/h2>\n\n\n\n
<\/div>\n\n\n\n
\n
\n
\"\"\/<\/a><\/figure>\n\n\n\n

Intelig\u00eancia Artificial – Uma Abordagem de Aprendizado de M\u00e1quina<\/strong><\/span><\/p>\n\n\n\n

Winner of the Brazilian Jabuti Prize (the most important literary award in Brazil), the book Intelig\u00eancia Artificial \u2013 Uma Abordagem de Aprendizado de M\u00e1quina<\/strong> addresses the main machine learning concepts and algorithms and points out ways to transform this knowledge into practical applications.<\/span><\/em><\/p>\n<\/div>\n\n\n\n

\n
\"\"<\/a><\/figure>\n\n\n\n

MDLText: An Efficient and Lightweight <\/strong><\/span>
Text Classifier<\/strong><\/span><\/p>\n\n\n\n

MDLText<\/strong> is an efficient, lightweight, scalable, and fast multinomial text classifier. It exhibits fast incremental learning and is<\/em> sufficiently robust to prevent overfitting, desirable features in real-world applications, large-scale problems, and online scenarios. <\/em><\/span>
The source code is available here<\/a>.<\/em><\/span><\/p>\n<\/div>\n\n\n\n

\n
\"\"<\/figure>\n\n\n\n

Exploitation Over Exploration: <\/strong><\/span>
Unmasking the Bias in Linear Bandit Recommender Offline Evaluation<\/strong><\/span><\/p>\n\n\n\n

This study conducts an extensive offline empirical comparison of several linear MABs. Our results expose significant inadequacies in offline evaluation protocols for bandits, particularly concerning their capacity to reflect true exploratory efficacy. The source code is available here<\/a>.<\/em><\/span><\/p>\n<\/div>\n<\/div>\n<\/div><\/div>\n\n\n\n

<\/div>\n\n\n\n
\n
\n
<\/div>\n\n\n\n

Books<\/h2>\n\n\n\n
\"\"<\/a><\/figure>
\n

Intelig\u00eancia Artificial – Uma Abordagem de Aprendizado de M\u00e1quina<\/strong> – 3rd Edition<\/h3>\n\n\n\n

[Artificial Intelligence – A Machine Learning Approach<\/em>]<\/h4>\n\n\n\n
K. FACELI, A.C. LORENA, J. GAMA, T.A. ALMEIDA, A.C.L.P.F. CARVALHO<\/h5>\n\n\n\n

ISBN: 9788521639213, 3rd Edition, LTC, 2025<\/p>\n\n\n\n

Winner of the Brazilian Jabuti Prize (the most important literary award in Brazil), the book Intelig\u00eancia Artificial \u2013 Uma Abordagem de Aprendizado de M\u00e1quina<\/strong> addresses the main machine learning concepts and algorithms and points out ways to transform this knowledge into practical applications.<\/p>\n\n\n\n

Available at: <\/span><\/p>\n\n\n\n