Archives de catégorie : Non classé

Intel Labs has created a novel framework for producing a class of parameter- and compute-efficient models called AttentionLite, which leverages recent advances in self-attention as a substitute for convolutions.

Neuroevolution-Enhanced Multi-Objective Optimization (NEMO) for Mixed-Precision Quantization delivers state-of-the-art compute speedups and memory improvements for artificial intelligence (AI) applications.

In this post, I introduce a metric for estimating the complexity level of your dataset and task, and I describe how to utilize it to optimize distillation performance.

This blog will outline the third class in this classification and its promising role in supporting machine understanding, context-based decision making, and other aspects of higher machine intelligence.

Our latest work, presented recently at the 2021 International Conference on Learning Representations (ICLR), forces a deep network to memorize some of the training examples by randomly changing their labels.

In this blog, I intend to explore this method further and investigate other test classification datasets and sub-tasks in an effort to duplicate these results.

We describe a scalable framework that combines Deep RL with genetic algorithms to search in extremely large combinatorial spaces to solve a critical memory allocation problem in hardware.

Model distillation is a powerful pruning technique, and in many use cases, it yields significant speedup and memory size reduction.

Machine learning requires us to have existing data — not the data our application will use when we run it, but data to learn from. 

Wei Li, Intel’s VP/GM AI & Analytics, discusses enabling an open AI ecosystem through Intel’s partnerships with Google, HuggingFace, and Accenture at the AI Summit in London.