Sep 4, 2020

Google Maps partners with DeepMind AI for improved ETAs

William Smith
2 min
With fellow Alphabet stablemate DeepMind, Google Maps ETA service has recently been improved through machine learning techniques
With fellow Alphabet stablemate DeepMind, Google Maps ETA service has recently been improved through machine learning techniques...

Thanks to its in-built technology, Google Maps offers functionality far and beyond that of the paper maps of old.

One of the most useful functions of navigation software such as Google Maps is parsing traffic data to provide estimates on arrival times and alternative routes- a great benefit to the users which Google says drive over one billion kilometres using Google Maps daily.

With fellow Alphabet stablemate DeepMind, a UK-based AI research company famous for the Victory of its AlphaGo platform over Go grandmaster Lee Sedol, that service has recently been improved through machine learning techniques.

While traffic data can be used to give the state of the roads at the present moment in time, Google also uses that data to predict what traffic will look like in the future, as Johann Lau, Product Manager, Google Maps, explained in a blog post. “To predict what traffic will look like in the near future, Google Maps analyzes historical traffic patterns for roads over time. For example, one pattern may show that the 280 freeway in Northern California typically has vehicles traveling at a speed of 65mph between 6-7am, but only at 15-20mph in the late afternoon. We then combine this database of historical traffic patterns with live traffic conditions, using machine learning to generate predictions based on both sets of data.”

While Google’s predictions for ETA were already 97% accurate, the partnership with DeepMind has involved using a machine learning technique known as Graph Neural Networks to improve that figure in cities worldwide by up to 50%, and to anticipate traffic that is yet to occur.

In its own blog post, DeepMind said: “Our model treats the local road network as a graph, where each route segment corresponds to a node and edges exist between segments that are consecutive on the same road or connected through an intersection. In a Graph Neural Network, a message passing algorithm is executed where the messages and their effect on edge and node states are learned by neural networks. From this viewpoint, our Supersegments are road subgraphs, which were sampled at random in proportion to traffic density. A single model can therefore be trained using these sampled subgraphs, and can be deployed at scale.” 

Share article

Jun 10, 2021

Google is using AI to design faster and improved processors

AI
ML
Google
processors
2 min
Google scientists claim their new method of designing Google’s AI accelerators has the potential to save thousands of hours of human effort

Engineers at Google are now using artificial intelligence (AI) to design faster and more efficient processors, and then using its chip designs to develop the next generation of specialised computers that run the same type of AI algorithms.

Google designs its own computer chips rather than buying commercial products, this allows the company to optimise the chips to run its own software, but the process is time-consuming and expensive, usually taking two to three years to develop.

Floorplanning, a stage of chip design, involves taking the finalised circuit diagram of a new chip and arranging the components into an efficient layout for manufacturing. Although the functional design of the chip is complete at this point, the layout can have a huge impact on speed and power consumption. 

Previously floorplanning has been a highly manual and time-consuming task, says Anna Goldie at Google. Teams would split larger chips into blocks and work on parts in parallel, fiddling around to find small refinements, she says.

Fast chip design

In a new paper, Googlers Azalia Mirhoseini and Anna Goldie, and their colleagues, describe a deep reinforcement-learning system that can create floorplans in under six hours. 

They have created a convolutional neural network system that performs the macro block placement by itself within hours to achieve an optimal layout; the standard cells are automatically placed in the gaps by other software. This ML system should be able to produce an ideal floorplan far faster than humans at the controls. The neural network gradually improves its placement skills as it gains experience, according to the AI scientists. 

In their paper, the Googlers said their neural network is "capable of generalising across chips — meaning that it can learn from experience to become both better and faster at placing new chips — allowing chip designers to be assisted by artificial agents with more experience than any human could ever gain."

Generating a floorplan can take less than a second using a pre-trained neural net, and with up to a few hours of fine-tuning the network, the software can match or beat a human at floorplan design, according to the paper, depending on which metric you use.

"Our method was used to design the next generation of Google’s artificial-intelligence accelerators, and has the potential to save thousands of hours of human effort for each new generation," the Googlers wrote. "Finally, we believe that more powerful AI-designed hardware will fuel advances in AI, creating a symbiotic relationship between the two fields.

Share article