We recently launched Vertex AI to help you move machine learning (ML) from experimentation into production faster and manage your models with confidence—speeding up your ability to improve outcomes at your organization.

But we know many of you are just getting started with ML and there’s a lot to learn! In tandem with building the Vertex AI platform, our teams are dropping as much best practices content as we can to help you come up to speed. Plus, we have a dedicated event on June 10th, Applied ML Summit, with sessions on how to apply ML technology in your projects, as well as grow your skills in this field. 

In the meantime, we couldn’t resist a quick lesson on hyperparameter tuning, because (a) it’s incredibly cool (b) you will impress your coworkers (c) Google Cloud has some unique battle tested tech in this area and (d) you will save time by getting better ML models into production faster. Vertex Vizier, on average, finds optimal parameters for complex functions in over 80% fewer trials than traditional methods. 

So it’s incredibly cool, but what is it?

While machine learning models automatically learn from data, they still require user-defined knobs which guide the learning process. These knobs, commonly known as hyperparameters, control, for example, the tradeoff between training accuracy and generalizability.  Examples of hyperparameters are the optimizer being used, its learning rate, regularization parameters, the number of hidden layers in a DNN, and their sizes.

Setting hyperparameters to their optimal values for a given dataset can make a huge difference in model quality. Typically, optimal hyperparameter values are found via grid searching a small number of combinations, or tedious manual experimentation. Hyperparameter tuning automates this work for you by searching for the best configuration of hyperparameters for optimal model performance. 

Vertex Vizier enables automated hyperparameter tuning in several ways:

1. “Traditional” hyperparameter tuning: by this we mean finding the optimal value of hyperparameters by measuring a single objective metric which is the output of an ML model.  For example, Vizier selects the number of hidden layers and their sizes, an optimizer and its learning rate, with the goal of maximizing model accuracy.
2. When hyperparameters are evaluated, models are trained and evaluated on splits of the data set. If evaluation metrics are streamed to Vizier (e.g. as a function of epoch) as the model is trained, Vizier’s early stopping algorithms can predict the final objective value, and recommend which unpromising trials should be early stopped. This conserves compute resources and speeds up convergence.
3. Oftentimes, models are tuned sequentially on different data sets. Vizier’s built in transfer learning learns priors from previous hyperparameter tuning studies, and leverages them to converge faster on subsequent hyperparameter tuning studies.
4. AutoML is a variant of #1, where Vertex Vizier performs both model selection, and also tunes architectures/non-architecture modifying hyperparameters. AutoML usually requires more code on top of Vertex Vizier (to ingest data etc), but Vizier is in most cases the “engine” behind the process. AutoML is implemented by defining a tree like (DAG) search space, rather than a “flat” search space (like in #1). Note that you can use DAG search spaces for any other purpose where searching over a hierarchical space makes sense.
5. There are times when you may wish to optimize more than one metric. For example, we would like to optimize model accuracy, while minimizing model latency. Vizier can find the Pareto frontier, which presents tradeoffs for multiple metrics, allowing users to choose the appropriate tradeoff. Simple example: I want to make a more accurate model, but would like to minimize serving latency. I do not know ahead of time what’s the tradeoff between the two metrics. Vizier can be used to explore and plot a tradeoff curve, so users can select on the most appropriate one. For example, “a latency decrease of 200ms will only decrease accuracy by 0.5%”

Google Vizier is all yours with Vertex AI

Google published the Vizier research paper in 2017, sharing our work and use cases for black-box optimization—i.e. The process of finding the best settings for a bunch of parameters or knobs when you can’t peer inside a system to see how well the knobs are working. The paper discusses our requirements, infrastructure design, underlying algorithms, and advanced features such as transfer learning that the service provides. Vizier has been essential to our progress with machine learning at Google, which is why we are so excited to make it available to you on Vertex AI.

Vizier has already tuned millions of ML models at Google, and its algorithms are continuously improved for faster convergence and handling of real-life edge cases. Vertex Vizier’s models are very well calibrated and are self-tuning (they adapt to user data), and offer unique power features, such as hierarchical search spaces and multi-objective optimization. We believe Vertex Vizier’s set of features is a unique capability to Google Cloud, and look forward to optimizing the quality of your models by automatically tuning hyperparameters for you.

To learn more about Vertex Vizier, check out these docs and if you are interested in what’s coming in machine learning over the next five years, tune in to our Applied ML Summit on June 10th, or watch the sessions on demand in your own time.

Start your 2022 New Year’s resolutions by learning at no cost how to use Google Cloud with the following training opportunities:

30 day access to Google Cloud Skills Boost 

Register by January 31, 2022 and claim 30 days free access to Google Cloud Skills Boost to complete the Getting Started with Google Cloud learning path. 

Google Cloud Skills Boost is the definitive destination for skills development where you can personalize learning paths, track progress, and validate your newly-earned expertise with skill badges. 

The Getting Started with Google Cloud learning path will give you the opportunity to earn three skill badges after you complete hands-on labs and courses designed for aspiring cloud engineers and architects. It covers the fundamentals of Google Cloud including core infrastructure, big data and ML, writing gcloud commands, using Cloud Shell, deploying virtual machines, and running containerized applications on GKE.

Cloud OnBoard: half day training on getting started with Google Cloud fundamentals

Attend the Getting Started Cloud OnBoard on January 20 for a comprehensive Google Cloud orientation. Google Cloud experts will show you how to execute your compute, available storage options, how to secure your data, and available Google Cloud managed services. 

Cloud Study Jam: expert-guided hands-on lab

Google Cloud experts will walk you through a hands-on lab included in Google Cloud Skill Boost’s Getting Started with Google Cloud learning path when you join our Cloud Study Jam on January 27. Google Cloud experts will also answer questions live via chat during this event.

In 2013, long before the world was discussing clean energy and sustainable practices, two IIT Madras graduates — Swapnil Jain and Tarun Mehta — had an idea to develop India’s first-ever electrical scooter.

This was at a time when auto manufacturers were still focusing on fossil-fuel-driven vehicles and ‘eco-friendly’ mobility solutions were more a trendy alternative catering to a niche market.

The duo founded Ather Energy in 2013 and launched their first fully-electric scooter, the Ather S340, in Bengaluru in 2016. Since then, the company has released several new models into the market and is planning to expand to eight more cities by the end of the year.

To support the smooth running of their vehicles, lower costs, improve time to market, and create great customer experience, Ather turned to Google Cloud.

Read the Full Story on YourStory

Commercial trucks often travel partially empty because many shippers don’t have enough cargo to fill an entire container or trailer. Although offering available space to other shippers helps minimize carbon emissions and reduce operating costs, most trucking companies can’t efficiently schedule, track, or deliver multiple freight loads.

Companies have always struggled to ship over-the-road freight efficiently. However,recent economic events have created an unprecedented logistics and transportation crisis that continues to disrupt supply chains, delay deliveries, and significantly raise the price of basic goods. Since some stores can’t keep their shelves fully stocked, many people across the country are finding it more difficult than ever to buy the things they need at an affordable price.

Although exacerbated by the pandemic, many of these supply chain issues have existed for decades. That’s why, in 2015, Flock Freight was started with the mission of reducing waste and inefficiency from the supply chain by reimagining the way freight moves. First to market with advanced algorithms that enable pooling shipments at scale, we create a new standard of service for shippers, increase revenue for carriers and reduce the impact of carbon emissions through shared truckload (STL) service.

Our technology helps lower prices compared to full truckload (FTL) by enabling shippers to only pay for the space they need—and maintain full control over pickup and delivery dates. Flock Freight also optimizes travel routes to speed up deliveries compared to traditional less than truckload (LTL), while eliminating unnecessary shipping hub transfers to minimize damage to cargo.

Today, thousands of shippers and trucking companies across the U.S. use Flock Freight to schedule shared truckloads, lower shipping costs, quickly deliver and track goods, and reduce their carbon footprint by up to 40%. Flock Freight further offsets carbon emissions by buying carbon credits for every FlockDirect™ guaranteed shared truckload shipment—at no extra cost to shippers.

Moving Flock Freight to Google Cloud

We founded Flock Freight with a small team based in southern California. We soon realized we needed a more scalable and affordable technology stack to support our rapidly growing platform and team. After joining the Google for Startups Cloud Program and consulting with dedicated Google startup experts, we decided to move all our data and applications to Google Cloud.

The highly secure-by-design infrastructure of Google Cloud now enables thousands of Flock Freight customers to move their freight faster, cheaper, and with less damage than traditional shipping methods. Specifically, we rely on Google Kubernetes Engine (GKE) to support the combinatorial optimization and machine learning (ML) algorithms and services that identify, pool, and schedule shared truckloads. We also leverage GKE to rapidly develop, deploy, and manage new applications and services.

In addition, we leverage Cloud SQL to automate database provisioning, storage capacity management, and other time-consuming tasks. Cloud SQL easily integrates with existing apps and Google Cloud services such as GKE and Pub/Sub. Lastly, we use Compute Engine to create and run virtual machines, optimize resource utilization, and lower computing costs by up to 91%. These cost savings allow us to shift more resources to R&D and rapidly develop new solutions and services for our customers.

Building a greener, more resilient, and responsive supply chain

The Google for Startups Cloud Program and dedicated Google startup experts were instrumental in helping us manage cloud infrastructure cost and maintaining very high SLAs, helping Flock Freight to focus on developing a comprehensive shipping platform that powers shared truckloads and drives positive industry change.

We especially want to highlight the Google Cloud research credits we relied on to launch Flock Freight and make rapid progress toward transforming the shipping industry. To this day, we continue to work with Google Cloud Managed Services partner DoiT International International to further scale and optimize operations on Google Cloud.

We’re proud of the results we’re delivering for our customers. For example, a home improvement importer now enjoys faster, safer, and easier shipping with 99.9% damage-free service and a 97.5% on-time delivery rate. A packaging supplier continues to maintain a 99% on-time delivery streak and decrease carbon emissions by 37%, while a mineral water company consistently reduces delivery expenses upwards of 50%.

Nationwide demand for shared truckloads continues to increase as the shipping industry works to lower costs and alleviate supply chain disruptions. With the Flock Freight platform, companies are building a more sustainable and resilient supply chain by efficiently combining multiple shipments into shared truckloads.

If you want to learn more about how Google Cloud can help your startup, visit our page here to get more information about our program, and sign up for our communications to get a look at our community activities, digital events, special offers, and more.

For a business to succeed in the long term, it needs to learn not just to adapt to inevitable change, but to harness it. South Africa-based PPS has been an insurance company since 1941 and today is the biggest mutual insurance provider in the country.

As a mutual company, PPS is owned by more than 200,000 members, making them shareholders. In recent years, PPS and other companies like it have been affected by a number of external factors.

“For one thing, technology platforms have brought in a new gig economy that has all kinds of implications for insurance,” says Avsharn Bachoo, CTO at PPS. “What we’ve been seeing is basically a disruption of the South African insurance industry. We chose to see that as an opportunity.”

“Our servers were at the end of their life cycle and we had to decide whether to refresh them or switch completely. To embrace the world of AI and machine learning effectively, we knew we needed a cloud-based infrastructure. We’ve found the answer in Google Cloud Platform.”

—Avsharn Bachoo, CTO, PPS

In early 2018, faced with an uncertain economic environment that was squeezing growth and profitability, PPS decided to transform itself from a traditional broker-based business into a digital insurance provider. A key pillar of this new strategy was to overhaul the company’s technology infrastructure. To turn the strategy into reality, Avsharn and his team chose Google Cloud Platform (GCP).

“Our servers were at the end of their life cycle and we had to decide whether to refresh them or switch completely,” says Avsharn. “To embrace the world of AI and machine learning (ML) effectively, we knew we needed a cloud-based infrastructure. We’ve found the answer in Google Cloud Platform.”

Power, speed, flexibility with Google Cloud Platform

Previously, PPS maintained an on-premises IT infrastructure, which worked for its traditional business but was unsuited for its new way of working. In early 2018, the company started working on new products for its members but this required large amounts of compute power that proved prohibitively expensive with on-premises servers. Even existing products were starting to require more than the infrastructure could deliver. Aging equipment meant that it’s testing and quality assurance environments bore little resemblance to the actual production environment.

“We had no pre-production environments at all,” says Avsharn, resulting in more work for developers after products had been released. Meanwhile, the capital required to buy and configure more servers for new projects meant fewer resources available for innovation, and left the company less able to react to changes in the market. PPS knew it had to find a cloud-based alternative.

Shortly after devising a new digital strategy, PPS engineers attended a training session on cloud infrastructure given by leading South African Google Cloud Partner Siatik. Impressed with the presentation, PPS engaged Siatik to help run a proof of concept for a cloud-based infrastructure, running on GCP. With on-site engineers and constant communication, Siatik formed a very close working relationship with PPS. “The team at Siatik was exemplary,” recalls Avsharn. “They were well-organized, with cutting-edge technical acumen and very creative solutions to our problems. They were real game-changers.”

“We wanted the platform to retrain its models in response to new data and improve its recommendations with more information. Normally this would be a manual process but Google Cloud ML Engine lets the models do this automatically.”

—Kimoon Kim, Lead Solution Architect and Data Engineer, Siatik

The proof of concept was successful, with GCP outperforming the existing infrastructure in terms of how it handled compute demands, databases, and storage.

“It’s the speed of GCP that really impresses us,” says Avsharn. PPS saw that GCP wasn’t just an opportunity to migrate its existing infrastructure to the cloud. With Siatik’s help, it redesigned its monolithic core architecture to one based around microservices using Google Kubernetes Engine (GKE). For data processing and storage, Cloud Dataflow and Cloud Datastore proved invaluable, while Stackdriver helped the IT team stay on top of logging and monitoring the system.

“Google Cloud makes migrations very easy,” says Brett St. Clair, CEO at Siatik. “It takes care of all the hard work with configurations and replications, so when we switch the machines on, everything is ready and working.”

The ease with which PPS migrated to GCP means that it can now tackle strategic goals much more quickly than before. The most ambitious of these is an AI-powered product recommendation platform. Information is collected from customers who opt in at a defined point in their journey, this database is queried using BigQuery, and the information is fed into the platform. The AI model then calculates the most appropriate products for each member, according to their personal history.

“Most of the product recommendation engines out there are based on clustering, where you’re offered products based on your peer groups,” explains Avsharn. “For the first time, we can make recommendations to members based on their individual preferences and historical behavior. That’s really powerful for us.”

Siatik helped PPS use TensorFlow and Cloud Machine Learning Engine to build the AI platform. For the engineers, these easy-to-use tools helped speed up the process considerably, allowing them to host the models locally without any fuss. Previously, it took one to three months to manually build the model and match an offer to a customer. With the AI platform, a match takes just a few minutes. Cloud ML Engine, in particular, helped the platform adapt to new information on the fly and easily make adjustments to its hyperparameters, that is, preset variables which define the model-training process.

“We wanted the platform to retrain its models in response to new data and improve its recommendations with more information,” says Kimoon Kim, Lead Solution Architect and Data Engineer at Siatik. “Normally this would be a manual process but Google Cloud ML Engine lets the models do this automatically.”

“Google Cloud helped us cancel out a lot of the noise around machine learning and AI. We don’t have to build new complicated algorithms or hire huge teams of data scientists to benefit. We just bring our data and use the right tools to focus on what’s really important.”

—Avsharn Bachoo, CTO, PPS

Harnessing artificial intelligence for real-world results

PPS deployed its new AI recommendation platform in December, 2018. Just a couple of months later, its impact was clear. “In around eight weeks, we saw a 5 percent growth in sales,” says Avsharn. “It’s been a direct result of building our recommendation platform with Google Cloud. We can offer the right products to the right members.”

For developers and engineers at PPS, working with Google Cloud gives them access to high performance technology and automation options with GKE. As a result, the infrastructure runs 70 percent faster than before with fewer cores and less memory. Developers can also work in mature testing environments, and for the first time, are able to build pre-production environments, leading to better quality products. More strategically, moving to a serverless, cloud-based infrastructure has helped PPS take control of its budget, moving away from intermittent, large capital spends to more manageable, project-to-project flows of operational expenditure. The company expects to see savings of around 50 percent, or $695,000.

“We have a lot more flexibility with our resources thanks to Google Cloud,” says Avsharn. “When we have a new idea, we don’t have to outlay new capital such as servers before we can even start working on it. We just spin up instances when we want and spin them back down when we’re done.”

With the AI platform deployed and working well, PPS is already looking at ways to improve it, including real-time updates and further automation. Soon, the company will integrate the platform with more sales campaigns for more effective targeting to boost sales even further. Meanwhile, it’s also experimenting with machine learning to spot patterns in data at scale for fraud analytics and risk assessment.

For PPS, working with Google Cloud has helped it transform quickly and effectively from disrupted to disruptor. The company is now looking to gain the same transformative effects by implementing G Suite for increased productivity and collaboration.

“Google Cloud helped us cancel out a lot of the noise around machine learning and AI,” says Avsharn. “We don’t have to build new complicated algorithms or hire huge teams of data scientists to benefit. We just bring our data and use the right tools to focus on what’s really important.”