Incremental Learning Through Deep Adaptation
نویسندگان
چکیده
منابع مشابه
Incremental Learning Through Deep Adaptation
Given an existing trained neural network, it is often desirable to be able to add new capabilities without hindering performance of already learned tasks. Existing approaches either learn sub-optimal solutions, require joint training, or incur a substantial increment in the number of parameters for each added task, typically as many as the original network. We propose a method which fully prese...
متن کاملRapid adaptation for deep neural networks through multi-task learning
We propose a novel approach to addressing the adaptation effectiveness issue in parameter adaptation for deep neural network (DNN) based acoustic models for automatic speech recognition by adding one or more small auxiliary output layers modeling broad acoustic units, such as mono-phones or tied-state (often called senone) clusters. In scenarios with a limited amount of available adaptation dat...
متن کاملIncremental Dictionary Learning for Unsupervised Domain Adaptation
Domain adaptation (DA) methods attempt to solve the domain mismatch problem between source and target data. In this paper, we propose an incremental dictionary learning method where some target data called supportive samples are selected to assist adaptation. The idea is partially inspired by the bootstrapping-based methods [1, 3], which choose from the target domain some samples and add them i...
متن کاملSVM Incremental Learning, Adaptation and Optimization
The objective of machine learning is to identify a model that yields good generalization performance. This involves repeatedly selecting a hypothesis class, searching the hypothesis class by minimizing a given objective function over the model’s parameter space, and evaluating the generalization performance of the resulting model. This search can be computationally intensive as training data co...
متن کاملTowards Incremental Learning with Deep Convolutional Networks
Deep neural networks are a powerful class of machine learning models. However they require a lot of time and computational resources to train. We propose to apply an incremental learning approach to train models by utilizing the information present in pre-trained models. We build towards this goal by studying the relationship between network architecture, categories in training data, the amount...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Pattern Analysis and Machine Intelligence
سال: 2020
ISSN: 0162-8828,2160-9292,1939-3539
DOI: 10.1109/tpami.2018.2884462