Tag: ai

Efficient inference on IMG Series4 NNAs

Research into neural network architectures generally prioritises accuracy over efficiency. Certain papers have investigated efficiency (Tan and Le 2020).

Self-compressing neural networks

The last decade of AI research has been characterised by the exploration of the potential of deep neural networks. The advances we have seen in recent.

Seeing what’s not there. IMG Series 4 NNA meets Visidon’s deep-learning-based Super Resolution technology.

Last year I read a fascinating article on LinkedIn about using deep-learning-based super-resolution networks to increase the apparent detail contained in.

Learning from the best: How nature can inspire AI research

Why should current-day AI researchers look into biology and the brain? We discuss in our latest AI research blog post.

Imagination’s neural network accelerator and Visidon’s denoising algorithm prove to be perfect partners

This blog post is a result of a collaboration between Visidon, headquartered in Finland and Imagination, based in the UK. Visidon is recognised as an.

Imagination and Humanising Autonomy Part 2: The humans behind the autonomy

Welcome to the second in a series of articles where we explore how Imagination and Humanising Autonomy, a UK-based AI behaviour company, are teaming up to.

High-Fidelity Conversion of Floating-Point Networks for Low-Precision Inference using Distillation

A major challenge for fast, low-power inference on neural network accelerators is the size of the models. There is a trend in recent years towards deeper.

Imagination and Humanising Autonomy Part 1: The path to safer roads

Welcome to the first in a series of articles where we explore how Imagination and Humanising Autonomy, a UK-based behaviour AI company, are teaming up to.

Reduced Operation Set Computing (ROSC) for Flexible, Future-Proof, High-Performance Inference

The versatility and power of deep learning means that modern neural networks have found myriad applications in areas as diverse as machine translation,.