What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Artificial neural network
Yann N. Dauphin mostly deals with Recurrent neural network, Artificial intelligence, Artificial neural network, Algorithm and Convolutional neural network.
Many of his studies on Artificial intelligence involve topics that are commonly interrelated, such as Machine learning.
His Artificial neural network research includes themes of High dimensional and Empirical risk minimization.
His biological study spans a wide range of topics, including Layer, Translation, Lipschitz continuity and Sequence learning.
His Layer research is multidisciplinary, incorporating perspectives in Computation and Variable length.
His Convolutional neural network research integrates issues from Modality, Feature, Facial expression and Test set.
His most cited work include:
- Theano: A Python framework for fast computation of mathematical expressions (1242 citations)
- Convolutional sequence to sequence learning (1236 citations)
- mixup: Beyond Empirical Risk Minimization (943 citations)
What are the main themes of his work throughout his whole career to date?
Yann N. Dauphin spends much of his time researching Artificial intelligence, Machine learning, Artificial neural network, Algorithm and Deep learning.
His work on Classifier as part of general Artificial intelligence study is frequently linked to Generalization, bridging the gap between disciplines.
His Machine learning research focuses on Language model and how it relates to Word and Decoding methods.
His work on Gradient descent, Recurrent neural network and Generalization error as part of general Artificial neural network study is frequently linked to Contextual image classification and Inverse problem, therefore connecting diverse disciplines of science.
His Algorithm research is multidisciplinary, relying on both Adversarial system, Layer, Convolutional neural network and Convolution.
His studies examine the connections between Layer and genetics, as well as such issues in Sequence learning, with regards to Computation and Translation.
He most often published in these fields:
- Artificial intelligence (57.53%)
- Machine learning (27.40%)
- Artificial neural network (23.29%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (57.53%)
- Machine learning (27.40%)
- Machine translation (10.96%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Machine learning, Machine translation, Language model and Deep learning.
His work on Artificial neural network as part of general Artificial intelligence study is frequently connected to Contextual image classification and Generalization, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
In the field of Machine learning, his study on Pruning overlaps with subjects such as Weighting.
His Machine translation study integrates concerns from other disciplines, such as Decoding methods and Translation.
His studies deal with areas such as Sentence, BLEU and Latent variable as well as Language model.
Yann N. Dauphin has researched Deep learning in several fields, including Automatic differentiation, Leverage and Singular value decomposition.
Between 2018 and 2021, his most popular works were:
- Pay Less Attention with Lightweight and Dynamic Convolutions (198 citations)
- Fixup Initialization: Residual Learning Without Normalization. (91 citations)
- Pay Less Attention with Lightweight and Dynamic Convolutions (80 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Artificial neural network
His main research concerns Artificial intelligence, Machine translation, Language model, Quadratic equation and Test set.
His work in Reinforcement learning and Deep learning is related to Artificial intelligence.
His research integrates issues of Regularization, Machine learning, Initialization and Residual in his study of Machine translation.
His Language model research is multidisciplinary, incorporating elements of Word and Coherence.
His Quadratic equation research spans across into areas like Automatic summarization, Convolution, Algorithm, Context and Element.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
