-
Chapter and Conference Paper
Multi-level Metric Learning for Few-Shot Image Recognition
Few-shot learning devotes to training a model on a few samples. Most of these approaches learn a model based on a pixel-level or global-level feature representation. However, using global features may lose loc...
-
Chapter and Conference Paper
Mismatched Design of Toroidal Surface Envelo** Conical Worm Drive
As is well known, mismatch modification is one of the important methods to reduce the sensitivity of line-contact gear transmission to error and deformation. In this paper, the mismatched design of the toroida...
-
Chapter and Conference Paper
Local Mutual Metric Network for Few-Shot Image Classification
Few-shot image classification aims to recognize unseen categories with only a few labeled training samples. Recent metric-based approaches tend to represent each sample with a high-level semantic representatio...
-
Chapter and Conference Paper
Application of MPE Model to Nickel Smelting
Nickel-sulfide minerals are normally associated with copper and iron sulfides and often contain a minor amount of valuable metals such as cobalt and detrimental impurities such as arsenic. Metal losses in slag...
-
Chapter and Conference Paper
Direct-to-Blister Copper Smelting with the ISASMELT™ Process
To date, many types of primary concentrate have been smelted using the ISASMELT™ technology, with annual smelting of copper concentrate alone exceeding 7 million tonnes. Most of this material could best be descri...
-
Chapter and Conference Paper
Fluxing Strategies for the Direct to Blister Smelting of High Silica and Low Iron Copper Concentrates
Copper concentrates which have high silica but low iron contents are difficult to smelt using conventional two stage smelting processes. Direct to blister smelting is possible using either iron oxide fluxes to...
-
Chapter and Conference Paper
Two-Level Verification of Data Integrity for Data Storage in Cloud Computing
Data storage in cloud computing can save capital expenditure and relive burden of storage management for users. As the lose or corruption of files stored may happen, many researchers focus on the verification ...
-
Chapter and Conference Paper
Scheduling Active Services in Clustered JBI Environment
Active services may cause business or runtime errors in clustered JBI environment. To cope with this problem, a scheduling mechanism is proposed. The overall scheduling framework and scheduling algorithm is gi...
-
Chapter and Conference Paper
Grey Reinforcement Learning for Incomplete Information Processing
New representation and computation mechanisms are key approaches for learning problems with incomplete information or in large probabilistic environments. In this paper, traditional reinforcement learning (RL)...
-
Chapter and Conference Paper
Quantum Reinforcement Learning
A novel quantum reinforcement learning is proposed through combining quantum theory and reinforcement learning. Inspired by state superposition principle, a framework of state value update algorithm is introdu...
-
Chapter and Conference Paper
An Autonomous Mobile Robot Based on Quantum Algorithm
In this paper, we design a novel autonomous mobile robot which uses quantum sensors to detect faint signals and fulfills some learning tasks using quantum reinforcement learning (QRL) algorithms. In this robot...