相关论文: Specialists and Generalists: Equilibrium Skill Acq…
As deep learning applications continue to become more diverse, an interesting question arises: Can general problem solving arise from jointly learning several such diverse tasks? To approach this question, deep multi-task learning is…
A primary goal of science and engineering (S & E) education is to produce good problem solvers, but how to best teach and measure the quality of problem-solving remains unclear. The process is complex, multifaceted, and not fully…
The standard view that creativity entails both originality and appropriateness leads to the paradox that experts who converge on one optimal solution are rated as no more creative than beginners who give many original solutions. This paper…
In this paper, we argue that current AI research operates on a spectrum between two different underlying conceptions of intelligence: Intelligence Realism, which holds that intelligence represents a single, universal capacity measurable…
Most machine learning theory and practice is concerned with learning a single task. In this thesis it is argued that in general there is insufficient information in a single task for a learner to generalise well and that what is required…
The integration of users and experts in machine learning is a widely studied topic in artificial intelligence literature. Similarly, human-computer interaction research extensively explores the factors that influence the acceptance of AI as…
A monopolist seller of multiple goods screens a buyer whose type is initially unknown to both but drawn from a commonly known distribution. The buyer privately learns about his type via a signal. We derive the seller's optimal mechanism in…
Current language models have demonstrated their capability to develop basic reasoning, but struggle in more complicated reasoning tasks that require a combination of atomic skills, such as math word problem requiring skills like arithmetic…
The survey is concerned with the issue of information transmission from experts to non-experts. Two main approaches to the use of experts can be traced. According to the game-theoretic approach expertise is a case of asymmetric information…
Involution now refers to the phenomenon that competitors in the same field make more efforts to struggle for limited resources but get lower individual ''profit effort ratio''. In this work, we investigate the evolution of the involution…
Humans and animals are able to generalize or transfer information from previous experience so that they can behave appropriately in novel situations. What mechanisms--computations, representations, and neural systems--give rise to this…
Modern demands of the statistics profession call for reimagining statistics training. The discipline needs to attract and develop students who are effective as real-world problem solvers, interdisciplinary collaborators, communicators,…
I examine the topic of training scientific generalists. To focus the discussion, I propose the creation of a new graduate program, analogous in structure to existing MD/PhD programs, aimed at training a critical mass of scientific…
A decision maker typically (i) incorporates training data to learn about the relative effectiveness of treatments, and (ii) chooses an implementation mechanism that implies an ``optimal'' predicted outcome distribution according to some…
Computers are quickly gaining on us. Artificial systems are now exceeding the performance of human experts in several domains. However, we do not yet have a deep definition of expertise. This paper examines the nature of expertise and…
Norms have been extensively proposed as coordination mechanisms for both agent and human societies. Nevertheless, choosing the norms to regulate a society is by no means straightforward. The reasons are twofold. First, the norms to choose…
We observe that incorporating a shared layer in a mixture-of-experts can lead to performance degradation. This leads us to hypothesize that learning shared features poses challenges in deep learning, potentially caused by the same feature…
Mathematicians have traditionally been a select group of academics that produce high-impact ideas allowing substantial results in several fields of science. Throughout the past 35 years, undergraduates enrolling in mathematics or statistics…
Modern human labor is characterized by specialization; we train for years and develop particular tools that allow us to perform well across a variety of tasks. In addition, AI agents have been specialized for domains such as software…
We consider the problem of strategic classification, where a learner must build a model to classify agents based on features that have been strategically modified. Previous work in this area has concentrated on the case when the learner is…