Related papers: Teaching Multiple Concepts to a Forgetful Learner

Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches…

We learn about the world from a diverse range of sensory information. Automated systems lack this ability as investigation has centred on processing information presented in a single form. Adapting architectures to learn from multiple…

Designing effective practice schedules for high-dimensional motor learning tasks remains a challenge, especially when skill states are unobservable and task performance may not reflect the true learning. We propose an automated curriculum…

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns…

This thesis explores the benefits machine learning algorithms can bring to online planning and scheduling for autonomous vehicles in off-road situations. Mainly, we focus on typical problems of interest which include computing itineraries…

Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time. To do this, systems need to handle the issue of catastrophic forgetting, where the…

We propose an adaptation of the curriculum training framework, applicable to state-of-the-art meta learning techniques for few-shot classification. Curriculum-based training popularly attempts to mimic human learning by progressively…

Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to…

Humans can progressively learn visual concepts from easy to hard questions. To mimic this efficient learning ability, we propose a competence-aware curriculum for visual concept learning in a question-answering manner. Specifically, we…

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

The development of data-informed predictive models for dynamical systems is of widespread interest in many disciplines. We present a unifying framework for blending mechanistic and machine-learning approaches to identify dynamical systems…

Multimodal learning seeks to combine data from multiple input sources to enhance the performance of different downstream tasks. In real-world scenarios, performance can degrade substantially if some input modalities are missing. Existing…

Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the right to be forgotten. However, existing unlearning methods are brittle: minor query modifications, such as…

We describe theoretical bounds and a practical algorithm for teaching a model by demonstration in a sequential decision making environment. Unlike previous efforts that have optimized learners that watch a teacher demonstrate a static…

Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its…

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful…

Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual learning paradigm faces the significant challenge…

Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This ability is limited in the current deep neural networks by a…

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent…

In this paper, we introduce a discrete variant of the meta-learning framework. Meta-learning aims at exploiting prior experience and data to improve performance on future tasks. By now, there exist numerous formulations for meta-learning in…