Related papers: Introduction to discoverology
Throughout life, we might seek a calling, companions, skills, entertainment, truth, self-knowledge, beauty, and edification. The practice of curiosity can be viewed as an extended and open-ended search for valuable information with hidden…
Research around AI for Science has seen significant success since the rise of deep learning models over the past decade, even with longstanding challenges such as protein structure prediction. However, this fast development inevitably made…
Exposure to ideas in domains outside a scientist's own may benefit her in reformulating existing research problems in novel ways and discovering new application domains for existing solution ideas. While improved performance in scholarly…
This paper explores the concept of "entropy of knowledge" (EoN) as a framework for understanding the challenges and complexities of scientific discovery. Drawing from principles in thermodynamics and information theory, I propose that the…
We address a not-widely-recognized subset of exploratory search, where a user sets out on a typically long "search quest" for the perfect wedding dress, overlooked research topic, killer company idea, etc. The first few outputs of current…
Theories of scientific and technological change view discovery and invention as endogenous processes, wherein prior accumulated knowledge enables future progress by allowing researchers to, in Newton's words, "stand on the shoulders of…
In this paper, we study the task of embodied interactive learning for object detection. Given a set of environments (and some labeling budget), our goal is to learn an object detector by having an agent select what data to obtain labels…
Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this…
Many reinforcement learning exploration techniques are overly optimistic and try to explore every state. Such exploration is impossible in environments with the unlimited number of states. I propose to use simulated exploration with an…
We discuss preliminary results from two experiments and put forth the notion that the development of sensory systems might be more geared towards discerning differences rather than for spotting similarities. We present the possibility that…
Scientists in some fields are concerned that many, or even most, published results are false. A high rate of false positives might arise accidentally, from shoddy research practices. Or it might be the inevitable result of institutional…
The Lecture-Tutorials for Introductory Astronomy have been designed to help introductory astronomy instructors actively engage their students in developing their conceptual understandings and reasoning abilities across a wide range of…
Scientific progress has long been understood as recombinant, with breakthroughs arising when existing ideas are joined in new ways. Empirical work in this tradition has focused on the inputs to discovery, asking whether a paper draws…
Innovation is to organizations what evolution is to organisms: it is how organisations adapt to changes in the environment and improve. Governments, institutions and firms that innovate are more likely to prosper and stand the test of time;…
While many sophisticated exploration methods have been proposed, their lack of generality and high computational cost often lead researchers to favor simpler methods like $\epsilon$-greedy. Motivated by this, we introduce $\beta$-DQN, a…
The Discovery Engine is a general purpose automated system for scientific discovery, which combines machine learning with state-of-the-art ML interpretability to enable rapid and robust scientific insight across diverse datasets. In this…
The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…
One of the remaining challenges in reinforcement learning is to develop agents that can generalise to novel scenarios they might encounter once deployed. This challenge is often framed in a multi-task setting where agents train on a fixed…
Many published research results are false, and controversy continues over the roles of replication and publication policy in improving the reliability of research. Addressing these problems is frustrated by the lack of a formal framework…
The past few centuries have witnessed a dramatic growth in scientific and technological knowledge. However, the nature of that growth - whether exponential or otherwise - remains controversial, perhaps partly due to the lack of quantitative…