Learnware: on the future of machine learning

By Zhi-Hua Zhou. 2016

161 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks (2022, background): “However, real-world applications often face the stream format data [7] and novel classes [8], [9], [10], [11], e.g., incoming hot topics in social media and new types of products in e-commerce.”
Co-Transport for Class-Incremental Learning (2021, background): “CIL for multimedia: It is common to observe the emergence of new classes in real-world applications [26, 32, 44, 52, 53, 55, 58, 65– 67].”
Learning Placeholders for Open-Set Recognition (2021, background): “However, this closed-world assumption comes to an end when the test set includes unseen categories [16, 2, 42, 35].”
Algorithms that remember: model inversion attacks and data protection law (2018, background): “The trend towards augmentable, pre-trained ‘learnware’ [12] appears to be accelerating.”
Distribution-Free One-Pass Learning (2017, background): “capability of adapting the distribution change that often occurs during the data accumulation process, which is also one of fundamental requirements of learnware [17].”
Experienced Optimization with Reusable Directional Model for Hyper-Parameter Search (2018, background): “Recently Zhou [Zhou, 2016] proposed the new concept of learnware, with properties of reusability, evolvability and comprehensibility.”
Learning with Feature and Distribution Evolvable Streams (2020, background): “As the data are usually collected from open and dynamic environments, it is of great importance to facilitate the learning system with the capability of dealing with the environmental changes (Dietterich, 2017), which is also one of the key requirements of learnware (Zhou, 2016).”
One-Pass Learning with Incremental and Decremental Features (2016, background): “Notice that the ability of adapting to environmental change is one of the fundamental requirements for learnware [4], whereas an important aspect is the ability of handling”
Heterogeneous Few-Shot Model Rectification With Semantic Mapping (2020, background): “Reusable is also emphasized as the fundamental properties of the learn-ware [1], which describes a novel perspective towards robust modeling.”
Multi-Instance Learning With Emerging Novel Class (2021, background): “However, both for binary or multi-class classiﬁcation, it is noteworthy that most previous studies on multi-instance learning were in a stable environment rather than an environment that is open and changes gradually [13], [14].”