This paper presents our experiences promoting active learning in programming courses from introductory to advanced levels. We use a variety of techniques as our courses vary greatly in size and our facilities vary in layout and equipment. For large lectures, we present active interludes that require students to work in small groups, respond to periodic polls, or help a professor program. For mo...

Reinforcement learners tend to repeat actions that led to satisfactory outcomes in the past, and avoid choices that resulted in unsatisfactory experiences. This behavior is one of the most widespread adaptation mechanisms in nature. In this paper we fully characterize the dynamics of one of the best known stochastic models of reinforcement learning [Bush, R., Mosteller, F., 1955. Stochastic Mod...

We consider the problem of learning an eeective behavior strategy from reward. Although much studied, the issue of how to use prior knowledge to scale optimal behavior learning up to real-world problems remains an important open issue. We investigate the inherent data-complexity of behavior learning when the goal is simply to optimize immediate reward. Although easier than reinforcement learnin...

Our previous work addressed the computational analysis of communities of Romanian online users involved in tourism activities and interested in sharing their impressions and experiences, by focusing on touristic content sharing and review sites. Our studies comprise several tasks such as sentiment analysis, keywords extraction and graph-based structuring of the users community. In this paper we...

This paper presents our experiences promoting active learning in programming courses from introductory to advanced levels. We use a variety of techniques as our courses vary greatly in size and our facilities vary in layout and equipment. For large lectures, we present active interludes that require students to work in small groups, respond to periodic polls, or help a professor program. For mo...

We consider the problem of learning an effective behavior strategy from reward. Although much studied, the issue of how to use prior knowledge to scale optimal behavior learning up to real-world problems remains an important open issue. We investigate the inherent data-complexity of behavior-learning when the goal is simply to optimize immediate reward. Although easier than reinforcement learni...

In this paper we propose the use of a novel learning paradigm in spoken language interfaces – implicitly-supervised learning. The central idea is to extract a supervision signal online, directly from the user, from certain patterns that occur naturally in the conversation. The approach eliminates the need for developer supervision and facilitates online learning and adaptation. As a first step ...

This study aims to investigate students’ perceptions of three aspects of learning – collaboration, selfregulated learning (SRL), and information seeking (IS) in both Internet-based and traditional face-to-face learning contexts. A multi-dimensional questionnaire was designed to evaluate each aspect in terms of perceived capability, experience, and interest. The analyses explore (1) potential di...

In this paper, we propose a memory-based Q-Iearning algorithm called predictive Q-routing (PQ-routing) for adaptive traffic control. We attempt to address two problems encountered in Q-routing (Boyan & Littman, 1994), namely, the inability to fine-tune routing policies under low network load and the inability to learn new optimal policies under decreasing load conditions. Unlike other memory-ba...

Supervised learning methods have long been used to allow musical interface designers to generate new mappings by example. We propose a method for harnessing machine learning algorithms within a radically interactive paradigm, in which the designer may repeatedly generate examples, train a learner, evaluate outcomes, and modify parameters in real-time within a single software environment. We des...