Journal Article10.1145/3386252
Generalizing from a Few Examples: A Survey on Few-shot Learning
TL;DR: A thorough survey to fully understand Few-shot Learning (FSL), and categorizes FSL methods from three perspectives: data, which uses prior knowledge to augment the supervised experience; model, which used to reduce the size of the hypothesis space; and algorithm, which using prior knowledgeto alter the search for the best hypothesis in the given hypothesis space.
read more
Abstract: Machine learning has been highly successful in data-intensive applications but is often hampered when the data set is small. Recently, Few-shot Learning (FSL) is proposed to tackle this problem. Using prior knowledge, FSL can rapidly generalize to new tasks containing only a few samples with supervised information. In this article, we conduct a thorough survey to fully understand FSL. Starting from a formal definition of FSL, we distinguish FSL from several relevant machine learning problems. We then point out that the core issue in FSL is that the empirical risk minimizer is unreliable. Based on how prior knowledge can be used to handle this core issue, we categorize FSL methods from three perspectives: (i) data, which uses prior knowledge to augment the supervised experience; (ii) model, which uses prior knowledge to reduce the size of the hypothesis space; and (iii) algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space. With this taxonomy, we review and discuss the pros and cons of each category. Promising directions, in the aspects of the FSL problem setups, techniques, applications, and theories, are also proposed to provide insights for future research.1
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning
Zheda Mai,Ruiwen Li,Hyunwoo Kim,Scott Sanner +3 more
- 01 Jun 2021
TL;DR: Supervised Contrastive Replay (SCR) as discussed by the authors encourages samples from the same class to cluster tightly in embedding space while pushing those of different classes further apart during replay-based training.
A survey on data‐efficient algorithms in big data era
TL;DR: In this paper, the authors present a comprehensive review of existing data-efficient methods and systematizes them into four categories: creating more data, transferring knowledge from rich data domains into poor data domains, altering data-hungry algorithms to reduce their dependency upon the amount of samples, or transferring knowledge between rich and poor domains.
Trustworthy AI: From Principles to Practices
16 Jan 2023
TL;DR: In this paper , the authors provide AI practitioners with a comprehensive guide for building trustworthy AI systems, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability.
Biological underpinnings for lifelong learning machines
Dhireesha Kudithipudi,Mario Aguilar-Simon,Jonathan Babb,Maxim Bazhenov,Douglas J. Blackiston,Josh C. Bongard,Andrew Brna,Suraj Chakravarthi Raja,Nick Cheney,Jeff Clune,Anurag Reddy Daram,S. Fusi,Peter Helfer,Leslie Kay,Nicholas A. Ketz,Zsolt Kira,Soheil Kolouri,Jeffrey L. Krichmar,Sam Kriegman,Michael Levin,Sandeep Reddy Madireddy,Santosh Manicka,Ali Marjaninejad,Bruce L. McNaughton,Risto Miikkulainen,Zaneta Navratilova,Tej Pandit,Alice Virginia Parker,Praveen K. Pilly,Sebastian Risi,Terrence J. Sejnowski,Andrea Soltoggio,Nicholas Soures,Andreas S. Tolias,Darío Urbina-Meléndez,Francisco J. Valero-Cuevas,Gido M. van de Ven,Joshua T. Vogelstein,Felix Wang,Ron Weiss,Angel Yanguas-Gil,Xinyun Zou,Hava T. Siegelmann +42 more
TL;DR: Kudithipudi et al. as mentioned in this paper identified a set of key capabilities that artificial systems will need to achieve lifelong learning, and discussed pathways to developing biologically inspired approaches for lifelong learning machines.
187
•Posted Content
Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations
TL;DR: This survey illustrates the concept of sequential recommendation, proposes a categorization of existing algorithms in terms of three types of behavioral sequence, and summarizes the key factors affecting the performance of DL-based models and conducts corresponding evaluations to demonstrate the effects of these factors.
179
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
99K
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
- 08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.