paper-with-me

홈 › Papers

Towards the One Learning Algorithm Hypothesis: A System-theoretic Approach

2021-12-04 · Christos Mavridis, John Baras

The existence of a universal learning architecture in human cognition is a widely spread conjecture supported by experimental findings from neuroscience. While no low-level implementation can be specified yet, an abstract outline of human perception and learning is believed to entail three basic properties: (a) hierarchical attention and processing, (b) memory-based knowledge representation, and (c) progressive learning and knowledge compaction. We approach the design of such a learning architecture from a system-theoretic viewpoint, developing a closed-loop system with three main components: (i) a multi-resolution analysis pre-processor, (ii) a group-invariant feature extractor, and (iii) a progressive knowledge-based learning module. Multi-resolution feedback loops are used for learning, i.e., for adapting the system parameters to online observations. To design (i) and (ii), we build upon the established theory of wavelet-based multi-resolution analysis and the properties of group convolution operators. Regarding (iii), we introduce a novel learning algorithm that constructs progressively growing knowledge representations in multiple resolutions. The proposed algorithm is an extension of the Online Deterministic Annealing (ODA) algorithm based on annealing optimization, solved using gradient-free stochastic approximation. ODA has inherent robustness and regularization properties and provides a means to progressively increase the complexity of the learning model i.e. the number of the neurons, as needed, through an intuitive bifurcation phenomenon. The proposed multi-resolution approach is hierarchical, progressive, knowledge-based, and interpretable. We illustrate the properties of the proposed architecture in the context of the state-of-the-art learning algorithms and deep learning methods.

📄 PDF Abstract BibTeX arXiv:2112.02256

Code (1)

mavridischristos/onlinedeterministicannealing 공식 구현

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Private Sequential Hypothesis Testing for Statisticians: Privacy, Error Rates, and Sample Size

2022-04-10 · Wanrong Zhang, Yajun Mei, Rachel Cummings

The sequential hypothesis testing problem is a class of statistical analyses where the sample size is not fixed in advance. Instead, the decision-process takes in new observations sequentially to make real-time decisions…

Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks

2019-05-25 · Jirong Yi, Hui Xie, Leixin Zhou, Xiaodong Wu 외

Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans…

Feature Compression

Monotonic Learning in the PAC Framework: A New Perspective

2025-01-09 · Ming Li, Chenyi Zhang, Qin Li

Monotone learning describes learning processes in which expected performance consistently improves as the amount of training data increases. However, recent studies challenge this conventional wisdom, revealing significa…

Learning TheoryPAC learning

Three Approaches for Personalization with Applications to Federated Learning

2020-02-25 · Yishay Mansour, Mehryar Mohri, Jae Ro, Ananda Theertha Suresh

The standard objective in machine learning is to train a single model for all users. However, in many learning scenarios, such as cloud computing and federated learning, it is possible to learn a personalized model per u…

AllBIG-bench Machine LearningCloud ComputingClustering+1

A Robust Hypothesis Test for Tree Ensemble Pruning

2023-01-24 · Daniel de Marchi, Matthew Welch, Michael Kosorok

Gradient boosted decision trees are some of the most popular algorithms in applied machine learning. They are a flexible and powerful tool that can robustly fit to any tabular dataset in a scalable and computationally ef…

Ensemble Pruning