What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Machine learning
His primary areas of study are Artificial intelligence, Speech recognition, Hidden Markov model, Pattern recognition and Natural language processing.
His Artificial intelligence research focuses on Machine learning and how it connects with Training set.
His studies deal with areas such as Vocabulary, Convolutional neural network and Noise as well as Speech recognition.
As a part of the same scientific study, he usually deals with the Hidden Markov model, concentrating on Context and frequently concerns with Comprehension.
In Pattern recognition, Li Deng works on issues like Noise reduction, which are connected to Key.
Li Deng has researched Natural language processing in several fields, including Semantics, Recurrent neural network and Information retrieval.
His most cited work include:
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups (6052 citations)
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition (2360 citations)
- Deep Neural Networks for Acoustic Modeling in Speech Recognition (1745 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Speech recognition, Hidden Markov model, Pattern recognition and Natural language processing.
His study connects Machine learning and Artificial intelligence.
Li Deng combines subjects such as Feature and Noise with his study of Speech recognition.
The study incorporates disciplines such as Context, Vocabulary and Markov chain, Markov model in addition to Hidden Markov model.
His biological study focuses on Mixture model.
His Artificial neural network research focuses on Time delay neural network in particular.
He most often published in these fields:
- Artificial intelligence (56.83%)
- Speech recognition (51.80%)
- Hidden Markov model (25.04%)
What were the highlights of his more recent work (between 2014-2020)?
- Artificial intelligence (56.83%)
- Natural language processing (18.27%)
- Artificial neural network (14.53%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Natural language processing, Artificial neural network, Deep learning and Machine learning are his primary areas of study.
His work deals with themes such as Speech recognition and Pattern recognition, which intersect with Artificial intelligence.
His research investigates the connection with Speech recognition and areas like Mixture model which intersect with concerns in Deep neural networks.
His research in Natural language processing intersects with topics in Context and Semantics.
His Artificial neural network research includes themes of Closed captioning, Tensor product, Unsupervised learning, Discriminative model and Big data.
As a member of one scientific family, he mostly works in the field of Deep learning, focusing on Machine translation and, on occasion, Phrase.
Between 2014 and 2020, his most popular works were:
- Stacked Attention Networks for Image Question Answering (1169 citations)
- From captions to visual concepts and back (934 citations)
- Embedding Entities and Relations for Learning and Inference in Knowledge Bases (855 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Artificial intelligence, Natural language processing, Natural language, Recurrent neural network and Deep learning are his primary areas of study.
His Artificial intelligence study integrates concerns from other disciplines, such as Machine learning and Speech recognition.
His work carried out in the field of Speech recognition brings together such families of science as Mixture model and Closed captioning.
The various areas that Li Deng examines in his Natural language processing study include End-to-end principle, Context and Information retrieval.
His Recurrent neural network study also includes
- Sentence which connect with Principle of maximum entropy, Convolutional neural network, Paragraph, Document retrieval and Web search engine,
- Spoken language which intersects with area such as Conditional random field, Frame, Knowledge engineering and Syntax,
- Benchmark that intertwine with fields like Pattern recognition,
- Salient that connect with fields like Leverage,
- Supervised learning that connect with fields like Domain knowledge, Learning classifier system and Representation.
His Deep learning research incorporates themes from Matching pursuit, Compressed sensing and Solver.
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.
