Related papers: Knowledge Flow: Improve Upon Your Teachers
Actual organizations, in particular the ones which operate in evolving and distributed environments, need advanced frameworks for the management of the knowledge life cycle. These systems have to be based on the social relations which…
Given a set of deep learning models, it can be hard to find models appropriate to a task, understand the models, and characterize how models are different one from another. Currently, practitioners rely on manually-written documentation to…
This paper introduces a new knowledge distillation method, called education distillation (ED), which is inspired by the structured and progressive nature of human learning. ED mimics the educational stages of primary school, middle school,…
We investigate a simple model for social learning with two agents: a teacher and a student. The teacher's goal is to teach the student the state of the world; however, the teacher himself is not certain about the state of the world and…
Although deep learning has made significant progress on fixed large-scale datasets, it typically encounters challenges regarding improperly detecting unknown/unseen classes in the open-world scenario, over-parametrized, and overfitting…
While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks. In this paper,…
Recent advancements in large language models (LLMs) and their multimodal variants have led to remarkable progress across various domains, demonstrating impressive capabilities and unprecedented potential. In the era of ubiquitous…
Knowledge tracing is a method used in education to assess and track the acquisition of knowledge by individual learners. It involves using a variety of techniques, such as quizzes, tests, and other forms of assessment, to determine what a…
While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models. In this paper, we aim…
While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they…
Education is a goal-oriented field. But if we want to treat education scientifically so we can accumulate, evaluate, and refine what we learn, then we must develop a theoretical framework that is strongly rooted in objective observations…
Educators are more than workers within educational systems; they are stewards of educational systems. They must analyze student performance data, identify patterns that inform targeted interventions and personalized learning plans,…
We introduce \textbf{Knowledge Swapping}, a novel task designed to selectively regulate knowledge of a pretrained model by enabling the forgetting of user\-specified information, retaining essential knowledge, and acquiring new knowledge…
Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model complexity. However, in most applications the compressed…
Knowledge distillation (KD) has demonstrated its effectiveness to boost the performance of graph neural networks (GNNs), where its goal is to distill knowledge from a deeper teacher GNN into a shallower student GNN. However, it is actually…
Creativity, i.e., the process of generating and developing fresh and original ideas or products that are useful or effective, is a valuable skill in a variety of domains. Creativity is called an essential 21st-century skill that should be…
This paper proposes a deep neural network approach for predicting multiphase flow in heterogeneous domains with high computational efficiency. The deep neural network model is able to handle permeability heterogeneity in high dimensional…
This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation. Our method…
With the rapid growth of knowledge, it shows a steady trend of knowledge fragmentization. Knowledge fragmentization manifests as that the knowledge related to a specific topic in a course is scattered in isolated and autonomous knowledge…
Deep learning has sparked a network of mutual interactions between different disciplines and AI. Naturally, each discipline focuses and interprets the workings of deep learning in different ways. This diversity of perspectives on deep…