With the AI revolution solidly underway, tech’s top 5 companies are investing huge amounts of money into AI development and AI engineering talent.
In the next few years, chipmaking giants and well-funded startups will race to gain market share.
Training a massive deep neural network can be daunting. Many deep learning (DL) engineers rely on TensorBoard for visualization so that they can better understand, debug, and optimize their model code.
The general perception of cloud computing is that it makes all compute tasks cheaper and easier to manage.
Imagine a world in which gradient descent or second-order methods have not yet been invented, and the only way to train machine learning models is to tune their weights by hand.
We are entering the golden age of artificial intelligence.
In a previous post on “What’s the deal with Neural Architecture Search?”, Liam Li and I discussed Neural Architecture Search (NAS) as a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures.
As most deep learning engineers know, it can take days or weeks to train a deep learning model, costing organizations considerable time and money. But what if we could speed up the process and achieve better results in the process?
Deep learning offers the promise of bypassing the process of manual feature engineering by learning representations in conjunction with statistical models in an end-to-end fashion.
In this post, we discuss how warm-starting can save computational resources and improve generalizability when training deep learning models.