Alex Graves is a computer scientist.

Education

Graves earned his

Bachelor of Science A Bachelor of Science (BS, BSc, B.S., B.Sc., SB, or ScB; from the Latin ') is a bachelor's degree that is awarded for programs that generally last three to five years. The first university to admit a student to the degree of Bachelor of Scienc ...

degree in

Theoretical Physics Theoretical physics is a branch of physics that employs mathematical models and abstractions of physical objects and systems to rationalize, explain, and predict List of natural phenomena, natural phenomena. This is in contrast to experimental p ...

from the

University of Edinburgh The University of Edinburgh (, ; abbreviated as ''Edin.'' in Post-nominal letters, post-nominals) is a Public university, public research university based in Edinburgh, Scotland. Founded by the City of Edinburgh Council, town council under th ...

and a PhD in

artificial intelligence Artificial intelligence (AI) is the capability of computer, computational systems to perform tasks typically associated with human intelligence, such as learning, reasoning, problem-solving, perception, and decision-making. It is a field of re ...

from the

Technical University of Munich The Technical University of Munich (TUM or TU Munich; ) is a public research university in Munich, Bavaria, Germany. It specializes in engineering, technology, medicine, and applied and natural sciences. Established in 1868 by King Ludwig II ...

supervised by

Jürgen Schmidhuber Jürgen Schmidhuber (born 17 January 1963) is a German computer scientist noted for his work in the field of artificial intelligence, specifically artificial neural networks. He is a scientific director of the Dalle Molle Institute for Artifici ...

at the

Dalle Molle Institute for Artificial Intelligence Research The Dalle Molle Institute for Artificial Intelligence (, IDSIA) is a research institute in the Lugano district of Canton Ticino, in southern Switzerland. It was founded in 1988 by Angelo Dalle Molle through the private Fondation Dalle Molle, and ...

Career and research

After his PhD, Graves was

postdoc A postdoctoral fellow, postdoctoral researcher, or simply postdoc, is a person professionally conducting research after the completion of their doctoral studies (typically a PhD). Postdocs most commonly, but not always, have a temporary academ ...

working with Schmidhuber at the

and

Geoffrey Hinton Geoffrey Everest Hinton (born 1947) is a British-Canadian computer scientist, cognitive scientist, and cognitive psychologist known for his work on artificial neural networks, which earned him the title "the Godfather of AI". Hinton is Univer ...

at the

University of Toronto The University of Toronto (UToronto or U of T) is a public university, public research university whose main campus is located on the grounds that surround Queen's Park (Toronto), Queen's Park in Toronto, Ontario, Canada. It was founded by ...

. At the

, Graves trained

long short-term memory Long short-term memory (LSTM) is a type of recurrent neural network (RNN) aimed at mitigating the vanishing gradient problem commonly encountered by traditional RNNs. Its relative insensitivity to gap length is its advantage over other RNNs, ...

(LSTM) neural networks by a novel method called

connectionist temporal classification Connectionist temporal classification (CTC) is a type of neural network output and associated scoring function, for training recurrent neural networks (RNNs) such as Long short-term memory, LSTM networks to tackle sequence problems where the timi ...

(CTC).Alex Graves, Santiago Fernandez, Faustino Gomez, and

(2006). Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural nets. Proceedings of ICML’06, pp. 369–376. This method outperformed traditional

speech recognition Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers. It is also ...

models in certain applications. In 2009, his CTC-trained LSTM was the first

recurrent neural network Recurrent neural networks (RNNs) are a class of artificial neural networks designed for processing sequential data, such as text, speech, and time series, where the order of elements is important. Unlike feedforward neural networks, which proces ...

(RNN) to win pattern recognition contests, winning several competitions in connected

handwriting recognition Handwriting recognition (HWR), also known as handwritten text recognition (HTR), is the ability of a computer to receive and interpret intelligible handwriting, handwritten input from sources such as paper documents, photographs, touch-screens ...

Google Google LLC (, ) is an American multinational corporation and technology company focusing on online advertising, search engine technology, cloud computing, computer software, quantum computing, e-commerce, consumer electronics, and artificial ...

uses CTC-trained LSTM for speech recognition on the

smartphone A smartphone is a mobile phone with advanced computing capabilities. It typically has a touchscreen interface, allowing users to access a wide range of applications and services, such as web browsing, email, and social media, as well as multi ...

.Google Research Blog. The neural networks behind Google Voice transcription. August 11, 2015. By Françoise Beaufays http://googleresearch.blogspot.co.at/2015/08/the-neural-networks-behind-google-voice.htmlGoogle Research Blog. Google voice search: faster and more accurate. September 24, 2015. By Haşim Sak, Andrew Senior, Kanishka Rao, Françoise Beaufays and Johan Schalkwyk – Google Speech Team http://googleresearch.blogspot.co.uk/2015/09/google-voice-search-faster-and-more.html Graves is also the creator of

neural Turing machine A neural Turing machine (NTM) is a recurrent neural network model of a Turing machine. The approach was published by Alex Graves et al. in 2014. NTMs combine the fuzzy pattern matching capabilities of neural networks with the algorithmic power of ...

s and the closely related

differentiable neural computer In artificial intelligence, a differentiable neural computer (DNC) is a memory augmented artificial neural network, neural network architecture (MANN), which is typically (but not by definition) recurrent in its implementation. The model was publ ...

. In 2023, he wrote the paper ''Bayesian Flow Networks''.

References

{{DEFAULTSORT:Graves, Alex Living people British artificial intelligence researchers Scottish computer scientists Alumni of the University of Edinburgh Year of birth missing (living people) Place of birth missing (living people)