Related papers: Iterative Teaching by Data Hallucination

Teachable agents are computer agents based on the pedagogical concept of learning-by-teaching. During the tutoring process, where students take on the role of the tutor to teach a computer agent tutee, learners have been observed to gain…

Imitation learning with a privileged teacher has proven effective for learning complex control behaviors from high-dimensional inputs, such as images. In this framework, a teacher is trained with privileged task information, while a student…

A typical assumption in state-of-the-art self-localization models is that an annotated training dataset is available for the target workspace. However, this is not necessarily true when a robot travels around the general open world. This…

A common assumption in machine learning is that training data are i.i.d. samples from some distribution. Processes that generate i.i.d. samples are, in a sense, uninformative---they produce data without regard to how good this data is for…

With fast developments in computational power and algorithms, deep learning has made breakthroughs and been applied in many fields. However, generalization remains to be a critical challenge, and the limited generalization capability…

We present a novel hierarchical triplet loss (HTL) capable of automatically collecting informative training samples (triplets) via a defined hierarchical tree that encodes global context information. This allows us to cope with the main…

Continual learning aims to sequentially learn new tasks without forgetting previous tasks' knowledge (catastrophic forgetting). One factor that can cause forgetting is the interference between the gradients on losses from different tasks.…

In real-world applications of education, an effective teacher adaptively chooses the next example to teach based on the learner's current state. However, most existing work in algorithmic machine teaching focuses on the batch setting, where…

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…

Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits. However, the state-of-the-art approaches are largely unsuitable in scarce data regimes.…

Humans can leverage hierarchical structures to split a task into sub-tasks and solve problems efficiently. Both imitation and reinforcement learning or a combination of them with hierarchical structures have been proven to be an efficient…

Continual learning is the problem of learning and retaining knowledge through time over multiple tasks and environments. Research has primarily focused on the incremental classification setting, where new tasks/classes are added at discrete…

It has been observed that neural networks perform poorly when the data or tasks are presented sequentially. Unlike humans, neural networks suffer greatly from catastrophic forgetting, making it impossible to perform life-long learning. To…

Artificial neural networks have exceeded human-level performance in accomplishing several individual tasks (e.g. voice recognition, object recognition, and video games). However, such success remains modest compared to human intelligence…

Despite achieving outstanding performance on various cross-modal tasks, current large vision-language models (LVLMs) still suffer from hallucination issues, manifesting as inconsistencies between their generated responses and the…

Rehearsal-based video incremental learning often employs knowledge distillation to mitigate catastrophic forgetting of previously learned data. However, this method faces two major challenges for video task: substantial computing resources…

Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing knowledge distillation methods direct the student to follow…

Most models of machine teaching and learning assume the learner makes no errors in its internal deductive inference. However, humans and large language models in few-shot learning regimes are two important examples of learners where this…

State-of-the-art deep learning algorithms generally require large amounts of data for model training. Lack thereof can severely deteriorate the performance, particularly in scenarios with fine-grained boundaries between categories. To this…

Deep neural networks (DNN) with a huge number of adjustable parameters remain largely black boxes. To shed light on the hidden layers of DNN, we study supervised learning by a DNN of width $N$ and depth $L$ consisting of $NL$ perceptrons…