Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204338434> ?p ?o ?g. }
- W3204338434 abstract "We propose a novel framework for classification using neural networks via an adversarial training procedure, in which we simultaneously train a main classifier—a neural network that solves the original classification task, i.e classifying instances into two main categories—and two meta-classifiers which act as discriminators and aim to detect false positives and negatives predicted by the original classifier. Our framework operates in two stages: In a first stage, both main and meta classifiers are pre-trained using the cross-entropy loss. The second stage consists of an adversarial training stage in which both main and meta classifiers are placed in a min-max game. Therefore, we switch to our new loss function so that the goal for the main classifier becomes to maximize the probability of failure of the adversarial meta-classifiers. Our training procedure can be explained by the fact that the meta-classifiers are more accurate when the main classifier is weak i.e., instances misclassified by the main classifier are naturally easy to separate and assign to the correct class membership. Opposingly, if the main classifier is robust enough, then the meta-classifiers are supposed to distinguish between instances that are naturally hard to classify, making thus more mistakes. In this work, both main and meta-classifiers are defined by Multi-Layer Perceptrons (MLP) and the entire training system is performed using backpropagation with gradient descent optimization. Experiments demonstrate the potential of our framework in outperforming the traditional learning scheme in improving the classification accuracy." @default.
- W3204338434 created "2021-10-11" @default.
- W3204338434 creator A5022458135 @default.
- W3204338434 creator A5065328227 @default.
- W3204338434 date "2021-07-18" @default.
- W3204338434 modified "2023-09-27" @default.
- W3204338434 title "Meta-Adversarial Training of Neural Networks for Binary Classification" @default.
- W3204338434 cites W1533861849 @default.
- W3204338434 cites W1565746575 @default.
- W3204338434 cites W1932122125 @default.
- W3204338434 cites W1969625066 @default.
- W3204338434 cites W1984202013 @default.
- W3204338434 cites W2003642451 @default.
- W3204338434 cites W2016879831 @default.
- W3204338434 cites W2022740958 @default.
- W3204338434 cites W2034416604 @default.
- W3204338434 cites W2062803420 @default.
- W3204338434 cites W2093953062 @default.
- W3204338434 cites W2098139515 @default.
- W3204338434 cites W2099471712 @default.
- W3204338434 cites W2100495367 @default.
- W3204338434 cites W2101156862 @default.
- W3204338434 cites W2131242650 @default.
- W3204338434 cites W2133924951 @default.
- W3204338434 cites W2138857742 @default.
- W3204338434 cites W2140833774 @default.
- W3204338434 cites W2141801655 @default.
- W3204338434 cites W2145106819 @default.
- W3204338434 cites W2163922914 @default.
- W3204338434 cites W2168545606 @default.
- W3204338434 cites W2297432279 @default.
- W3204338434 cites W2523246573 @default.
- W3204338434 cites W2549961271 @default.
- W3204338434 cites W2612637113 @default.
- W3204338434 cites W2762941833 @default.
- W3204338434 cites W2770173563 @default.
- W3204338434 cites W2791006446 @default.
- W3204338434 cites W2884547199 @default.
- W3204338434 cites W2911244395 @default.
- W3204338434 cites W2919115771 @default.
- W3204338434 cites W2921283782 @default.
- W3204338434 cites W2963416883 @default.
- W3204338434 cites W2963744840 @default.
- W3204338434 cites W2963942586 @default.
- W3204338434 cites W2964082701 @default.
- W3204338434 cites W2964121744 @default.
- W3204338434 cites W2964159205 @default.
- W3204338434 cites W3093419064 @default.
- W3204338434 cites W3101813844 @default.
- W3204338434 cites W3120740533 @default.
- W3204338434 doi "https://doi.org/10.1109/ijcnn52387.2021.9534247" @default.
- W3204338434 hasPublicationYear "2021" @default.
- W3204338434 type Work @default.
- W3204338434 sameAs 3204338434 @default.
- W3204338434 citedByCount "0" @default.
- W3204338434 crossrefType "proceedings-article" @default.
- W3204338434 hasAuthorship W3204338434A5022458135 @default.
- W3204338434 hasAuthorship W3204338434A5065328227 @default.
- W3204338434 hasConcept C106135958 @default.
- W3204338434 hasConcept C119857082 @default.
- W3204338434 hasConcept C12267149 @default.
- W3204338434 hasConcept C139532973 @default.
- W3204338434 hasConcept C153180895 @default.
- W3204338434 hasConcept C154945302 @default.
- W3204338434 hasConcept C155032097 @default.
- W3204338434 hasConcept C37736160 @default.
- W3204338434 hasConcept C41008148 @default.
- W3204338434 hasConcept C50644808 @default.
- W3204338434 hasConcept C60908668 @default.
- W3204338434 hasConcept C66905080 @default.
- W3204338434 hasConcept C95623464 @default.
- W3204338434 hasConceptScore W3204338434C106135958 @default.
- W3204338434 hasConceptScore W3204338434C119857082 @default.
- W3204338434 hasConceptScore W3204338434C12267149 @default.
- W3204338434 hasConceptScore W3204338434C139532973 @default.
- W3204338434 hasConceptScore W3204338434C153180895 @default.
- W3204338434 hasConceptScore W3204338434C154945302 @default.
- W3204338434 hasConceptScore W3204338434C155032097 @default.
- W3204338434 hasConceptScore W3204338434C37736160 @default.
- W3204338434 hasConceptScore W3204338434C41008148 @default.
- W3204338434 hasConceptScore W3204338434C50644808 @default.
- W3204338434 hasConceptScore W3204338434C60908668 @default.
- W3204338434 hasConceptScore W3204338434C66905080 @default.
- W3204338434 hasConceptScore W3204338434C95623464 @default.
- W3204338434 hasFunder F4320320879 @default.
- W3204338434 hasFunder F4320321114 @default.
- W3204338434 hasLocation W32043384341 @default.
- W3204338434 hasOpenAccess W3204338434 @default.
- W3204338434 hasPrimaryLocation W32043384341 @default.
- W3204338434 hasRelatedWork W1977379296 @default.
- W3204338434 hasRelatedWork W2052003713 @default.
- W3204338434 hasRelatedWork W2149078746 @default.
- W3204338434 hasRelatedWork W2170335817 @default.
- W3204338434 hasRelatedWork W2550800442 @default.
- W3204338434 hasRelatedWork W2797734191 @default.
- W3204338434 hasRelatedWork W3158472548 @default.
- W3204338434 hasRelatedWork W3204338434 @default.
- W3204338434 hasRelatedWork W4221015625 @default.
- W3204338434 hasRelatedWork W4249229055 @default.
- W3204338434 isParatext "false" @default.