Nvidia’s greatest growth in chips in 2017 was in the AI and cloud-based sectors, which should increase in 2018.

This year tech companies will begin moving AI more to the “edge” of access, leveraging trained machine learning software with cloud-based computing, according to a VentureBeat.com article co-written by two executives at Madrona Venture Group, a high-tech venture capital fund.

The authors, Daniel Li, Principal, and S. Somasegar, Managing Director, predicted four new trends in 2018:

1. Moving out: Intelligence on the Edge

Machine learning models will operate outside of the data centers and via phones and personal assistant devices, like Alexa and SIRI to reduce power and bandwidth consumption, reduce latency and ensure privacy.

2. Moving Down: Purpose-built AI Hardware

Specialized chips for AI will perform better than all-purpose chips, and computers built to optimize AI are already being designed.

3. Moving Out: Natural User Interfaces

Text, voice, gestures and vision will all be used more widely to communicate with systems. Voice activated speakers are already being used by 35 million consumers.

4.     Moving Up: Vertical AI Applications

Apps will be created and tailored for specific markets to rapidly address customer needs.