Skip to main content
European Commission logo
español español
CORDIS - Resultados de investigaciones de la UE
CORDIS
CORDIS Web 30th anniversary CORDIS Web 30th anniversary

Formal verification and neural lossless compression

Descripción del proyecto

Dos nuevos paradigmas de compresión

Existe un subcampo del aprendizaje automático que se ocupa de los algoritmos inspirados en el cerebro.Se trata del aprendizaje profundo, que cada vez se utiliza más como base para los sistemas de compresión de datos. Las redes neuronales forman parte del enfoque de aprendizaje profundo de la inteligencia artificial. El equipo del proyecto NNESCI, que cuenta con el apoyo de las Acciones Marie Skłodowska-Curie, analizará los algoritmos de compresión paralela para comprimir con eficacia enormes cantidades de datos. En concreto, el equipo del proyecto desarrollará dos nuevos paradigmas de compresión. El primero utilizará modelos generativos basados en convoluciones tridimensionales, aplicados a imágenes médicas. El segundo es la compresión de audio y vídeo mediante modelos de variables latentes de series temporales. En el proyecto también se diseñará un lenguaje específico para cada dominio.

Objetivo

Techniques based on neural networks (NNs), the study of which is often referred to as ‘deep learning’, have recently been shown to be extremely effective as a basis for data compression systems. I will develop the new field of ‘neural compression’, which has emerged around these ideas, focussing primarily on lossless compression in the two directions which I believe are most important:

Scale: NNs go hand in hand with parallel hardware, and I will investigate new parallel compression algorithms for efficiently compressing huge quantities of data. Specifically, I will develop two entirely new compression paradigms: Firstly, compression of volumetric images using generative models based on 3D convolutions, applied to medical imaging, where teleradiology and new cloud-based analysis make the need for efficient compression particularly acute. And secondly, compression of audio and video using time-series latent variable models, known as ‘state space models’, which offer uniquely efficient utilization of parallel hardware.

Systems: I will research, design and implement a domain specific language (DSL) for concisely expressing codecs which are guaranteed to be lossless by construction. Until now, implementations of compression systems always separate the implementation of the encoder from the decoder, and rely on an ad-hoc debugging and testing process to ensure that data are recovered correctly. During my PhD, I discovered that it is sometimes possible for a computer to automatically convert an encoder function into a decoder, and vice versa, potentially halving the amount of code. I will explore the limits, in terms of flexibility and efficiency, of this novel idea, using insights from ‘automatic differentiation’, a related functional transformation, on which I am a leading expert.

Coordinador

UNIVERSITEIT VAN AMSTERDAM
Aportación neta de la UEn
€ 187 624,32
Dirección
SPUI 21
1012WX Amsterdam
Países Bajos

Ver en el mapa

Tipo de actividad
Higher or Secondary Education Establishments
Enlaces
Coste total
Sin datos