Evolutionary algorithms have emerged as a robust alternative to traditional greedy approaches for decision tree induction. By mimicking the natural selection process, these algorithms iterate over a ...

Evolutionary algorithms (EAs) represent a class of heuristic optimisation methods inspired by natural selection and Mendelian genetics. They iteratively evolve a population of candidate solutions ...

Evolutionary reinforcement learning is an exciting frontier in machine learning, combining the strengths of two distinct approaches: reinforcement learning and evolutionary computation. In ...

Social Indicators Research, Vol. 135, No. 1 (January 2018), pp. 1-14 (14 pages) In this paper we propose a data-driven approach for the construction of survey-based indicators using large data sets.

Large language models (LLMs) leverage unsupervised learning to capture statistical patterns within vast amounts of text data. At the core of these models lies the Transformer architecture, which ...

Scientists have prototyped a new method for 'rationally engineering' enzymes to deliver improved performance. They have devised an algorithm, which takes into account an enzyme's evolutionary history, ...

The Center studies the behavior of complex biological, computational and social systems through a collaborative and ...

The following essay is reprinted with permission from The Conversation, an online publication covering the latest research. People’s daily interactions with online algorithms affect how they learn ...

Harvard Faculty of Arts and Sciences has officially voted to change the name of the Human Evolutionary Biology concentration during a meeting on April 1. Effective as of July 1, 2025 — when the ...