FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2977408082> ?p ?o ?g. }

• W2977408082 abstract "Artificial neural networks have exceeded human-level performance in accomplishing several individual tasks (e.g. voice recognition, object recognition, and video games). However, such success remains modest compared to human intelligence that can learn and perform an unlimited number of tasks. Humans' ability of learning and accumulating knowledge over their lifetime is an essential aspect of their intelligence. Continual machine learning aims at a higher level of machine intelligence through providing the artificial agents with the ability to learn online from a non-stationary and never-ending stream of data. A key component of such a never-ending learning process is to overcome the catastrophic forgetting of previously seen data, a problem that neural networks are well known to suffer from. The work described in this thesis has been dedicated to the investigation of continual learning and solutions to mitigate the forgetting phenomena in neural networks. To approach the continual learning problem, we first assume a task incremental setting where tasks are received one at a time and data from previous tasks are not stored. Since the task incremental setting can't be assumed in all continual learning scenarios, we also study the more general online continual setting. We consider an infinite stream of data drawn from a non-stationary distribution with a supervisory or self-supervisory training signal. The proposed methods in this thesis have tackled important aspects of continual learning. They were evaluated on different benchmarks and over various learning sequences. Advances in the state of the art of continual learning have been shown and challenges for bringing continual learning into application were critically identified." @default.
• W2977408082 created "2019-10-10" @default.
• W2977408082 creator A5021198356 @default.
• W2977408082 date "2019-10-07" @default.
• W2977408082 modified "2023-09-27" @default.
• W2977408082 title "Continual Learning in Neural Networks." @default.
• W2977408082 cites W114517082 @default.
• W2977408082 cites W1467353089 @default.
• W2977408082 cites W1498436455 @default.
• W2977408082 cites W1542791059 @default.
• W2977408082 cites W1566538838 @default.
• W2977408082 cites W1567697449 @default.
• W2977408082 cites W1579279110 @default.
• W2977408082 cites W1579705726 @default.
• W2977408082 cites W1595483645 @default.
• W2977408082 cites W1598866093 @default.
• W2977408082 cites W1682403713 @default.
• W2977408082 cites W1686810756 @default.
• W2977408082 cites W1757796397 @default.
• W2977408082 cites W1821462560 @default.
• W2977408082 cites W1846799578 @default.
• W2977408082 cites W1932198206 @default.
• W2977408082 cites W1935978687 @default.
• W2977408082 cites W1942758450 @default.
• W2977408082 cites W1943830695 @default.
• W2977408082 cites W1963882359 @default.
• W2977408082 cites W196757127 @default.
• W2977408082 cites W1977544285 @default.
• W2977408082 cites W1992156285 @default.
• W2977408082 cites W2016973429 @default.
• W2977408082 cites W2017257315 @default.
• W2977408082 cites W2018124860 @default.
• W2977408082 cites W2035424729 @default.
• W2977408082 cites W2036963181 @default.
• W2977408082 cites W2040468026 @default.
• W2977408082 cites W2047057213 @default.
• W2977408082 cites W2047125104 @default.
• W2977408082 cites W2048226872 @default.
• W2977408082 cites W2060277733 @default.
• W2977408082 cites W2061524864 @default.
• W2977408082 cites W2072128103 @default.
• W2977408082 cites W2075187489 @default.
• W2977408082 cites W2077723394 @default.
• W2977408082 cites W2081354168 @default.
• W2977408082 cites W2094426896 @default.
• W2977408082 cites W2095705004 @default.
• W2977408082 cites W2099049980 @default.
• W2977408082 cites W2100495367 @default.
• W2977408082 cites W2100602534 @default.
• W2977408082 cites W2102605133 @default.
• W2977408082 cites W2112796928 @default.
• W2977408082 cites W2113839990 @default.
• W2977408082 cites W2115599650 @default.
• W2977408082 cites W2116522068 @default.
• W2977408082 cites W2117539524 @default.
• W2977408082 cites W2119885577 @default.
• W2977408082 cites W2121358800 @default.
• W2977408082 cites W2131479143 @default.
• W2977408082 cites W2134807560 @default.
• W2977408082 cites W2135046866 @default.
• W2977408082 cites W2137884112 @default.
• W2977408082 cites W2138011018 @default.
• W2977408082 cites W2138733328 @default.
• W2977408082 cites W2139759436 @default.
• W2977408082 cites W2142165428 @default.
• W2977408082 cites W2145339207 @default.
• W2977408082 cites W2146502635 @default.
• W2977408082 cites W2150621701 @default.
• W2977408082 cites W2150884987 @default.
• W2977408082 cites W2152161678 @default.
• W2977408082 cites W2155541015 @default.
• W2977408082 cites W2156387975 @default.
• W2977408082 cites W2163605009 @default.
• W2977408082 cites W2181083374 @default.
• W2977408082 cites W2189774688 @default.
• W2977408082 cites W2226087478 @default.
• W2977408082 cites W22297218 @default.
• W2977408082 cites W2294543795 @default.
• W2977408082 cites W2311414730 @default.
• W2977408082 cites W2336829997 @default.
• W2977408082 cites W2340897893 @default.
• W2977408082 cites W2414711238 @default.
• W2977408082 cites W2533598788 @default.
• W2977408082 cites W2553902701 @default.
• W2977408082 cites W2554616628 @default.
• W2977408082 cites W2559403207 @default.
• W2977408082 cites W2560647685 @default.
• W2977408082 cites W2565989828 @default.
• W2977408082 cites W2583761661 @default.
• W2977408082 cites W2583938035 @default.
• W2977408082 cites W2599437901 @default.
• W2977408082 cites W2605998369 @default.
• W2977408082 cites W2609002182 @default.
• W2977408082 cites W2612112834 @default.
• W2977408082 cites W2614634292 @default.
• W2977408082 cites W2617118670 @default.
• W2977408082 cites W2619890685 @default.
• W2977408082 cites W2742079690 @default.
• W2977408082 cites W2753248866 @default.
• W2977408082 cites W2761873684 @default.

• next