相关论文: Learning to Multi-Task by Active Sampling

During recent years, active learning has evolved into a popular paradigm for utilizing user's feedback to improve accuracy of learning algorithms. Active learning works by selecting the most informative sample among unlabeled data and…

Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network…

Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task…

Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilizes self-supervised…

A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has…

Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider…

Many well-trained Convolutional Neural Network(CNN) models have now been released online by developers for the sake of effortless reproducing. In this paper, we treat such pre-trained networks as teachers and explore how to learn a target…

Most recent successes in robot reinforcement learning involve learning a specialized single-task agent. However, robots capable of performing multiple tasks can be much more valuable in real-world applications. Multi-task reinforcement…

One of the biggest challenges that complicates applied supervised machine learning is the need for huge amounts of labeled data. Active Learning (AL) is a well-known standard method for efficiently obtaining labeled data by first labeling…

Multimodal meta-learning is a recent problem that extends conventional few-shot meta-learning by generalizing its setup to diverse multimodal task distributions. This setup makes a step towards mimicking how humans make use of a diverse set…

Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years. Most of the…

Active learning is a practical field of machine learning that automates the process of selecting which data to label. Current methods are effective in reducing the burden of data labeling but are heavily model-reliant. This has led to the…

Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such…

Shared training approaches, such as multi-task learning (MTL) and gradient-based meta-learning, are widely used in various machine learning applications, but they often suffer from negative transfer, leading to performance degradation in…

Active learning has the potential to be especially useful for messy, uncurated pools where datapoints vary in relevance to the target task. However, state-of-the-art approaches to this problem currently rely on using fixed, unsupervised…

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…

The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We introduce a conditional neural process based approach to…

Purpose: Surgery scene understanding with tool-tissue interaction recognition and automatic report generation can play an important role in intra-operative guidance, decision-making and postoperative analysis in robotic surgery. However,…

While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is fixed. Due to such…

Lifelong learning can be viewed as a continuous transfer learning procedure over consecutive tasks, where learning a given task depends on accumulated knowledge --- the so-called knowledge base. Most published work on lifelong learning…