Search Results

How to accurately learn task-relevant state representations from high-dimensional observations with visual distractions is a realistic and challenging problem in visual reinforcement learning. Recently, unsupervised representation learning ...

One of the major challenges in reinforcement learning (RL) is its applications in episodic tasks, such as chess game, molecular structure design, healthcare, among others, where the rewards in such scenarios are usually sparse and can only be ...

• A method that can efficiently solve episodic tasks with only trajectory feedback.
• State-entropy based exploration and uniform reward redistribution trade-off.
• Outstanding experimental results in tasks with episodic reward on ...

Transfer learning (TL) is an information reuse learning tool, which can help us learn better classification effect than traditional single task learning, because transfer learning can share information within the task-to-task model. Most TL algorithms are ...

In microservice systems, the identification of root causes of anomalies is imperative for service reliability and business impact. This process is typically divided into two phases: (i)constructing a service dependency graph that outlines the sequence ...

Compared with single-task learning, multi-tasks can obtain better classifiers by the information provided by each task. In the process of multi-task data collection, we always focus on the target task data in the training process, and ...

Near-Data Processing (NDP) has been a promising architectural paradigm to address the memory wall challenge for data-intensive applications. Typical NDP systems based on 3D-stacked memories contain massive parallel processing units, each of which can ...

Universum, as third class that does not belong to the positive class and negative class, allows to incorporate the prior knowledge into the learning process. A lot of reaserchers confirmed that Universum is helpful in the supervised ...

Positive and unlabeled learning (PU learning) is a kind of problem whose goal is learning a two-classes classifier with little proportion of positive samples and numerous unlabeled samples. A series of studies focus on how to extract ...

In recent years, contrastive learning has become an important technology of self-supervised representation learning and achieved SOTA performances in many fields, which has also gained increasing attention in the reinforcement learning (RL) ...

Graph mining is an emerging application of high importance and also with high complexity, thus requiring efficient hardware acceleration. Current accelerator designs only utilize coarse-grained parallelism, leaving large room for further optimizations. ...

Deep reinforcement learning (DRL) has achieved great success in recent years by combining the feature extraction power of deep learning and the decision power of reinforcement learning techniques. In the literature, Convolutional ...

• Gated multi-attention module is proposed to eliminate task-irrelevant attentions.

Automated discovery of geometric theorems has attracted considerable attention from the research community. In this paper, a new method is proposed to discover geometric theorems automatically. This method first generates vector equations based on ...

Deep Neural Network (DNN) has been widely adopted in video analysis application. The computation involved in DNN is more efficient on GPUs than on CPUs. However, recent serving systems involve the low utilization of GPU, due to limited process ...