Connect with us

Cars

Intel-backed startup Nyansa chases the total problem in the AI of network monitoring

Published

on

There are many opinions about what matters most in machine learning. Some would say it’s the data, some would say it is the algorithms and equations used to train computers on that data. Still, others would say it is the formulation of the question itself that is most important in machine learning.

The last point of view is representative of a startup called Nyansa, composed of networking veterans and big data specialists who believe they have a better approach to network management than, say, Cisco Systems or Hewlett-Packard Enterprise.

The reason, according to chief technologist and co-founder Anand Srinivas, is because Nyansa figures out all the different parts of a system — not just the switches and wireless access points, but the applications as well, that can affect what an end user experiences.

“Our innovation is not inventing new machine learning algorithms, it is in terms of bringing machine-learning algorithms to a use case like networking,” Srinivas said in an interview with ZDNet on Monday. Srinivas holds a PhD in wireless networks and algorithms from MIT, and has held a number of industry positions, especially for software-defined networking, at firms such as Overture Networks, Plexxi, and Airvana.

Also: Network technologies are changing faster than we can manage them

Based in Palo Alto, four-and-half-year-old Nyansa sells tools to IT to monitor the health of the network, explain degradations of performance when they happen, and then propose solutions. Its tools run on Amazon’s AWS, though they can also be installed on-premise, with hooks back to the public cloud. The company has over 100 customers, representing over 10 million devices “under observation,” it says, across 200,000 access points from different vendors, on hundreds of production networks. Clients include Uber, Tesla, and Lululemon. It has been bankrolled by chip giant Intel’s investment arm, and Formation8, to the tune of $27 million.

Its machine learning tools are very simple, far less sophisticated or adventuresome than today’s deep learning neural network approaches. They include things such as logistic regression analysis, random forest searches, nearest-neighbor searches, and “cluster” analysis. “A lot of this is off-the-shelf stuff,” confesses Srinivas.

“It is more straightforward than deep learning; deep learning is not the right approach for us, not yet, not until we grab all the low-hanging fruit which the simpler kinds of machine learning algorithms can give us.”

Nyansa gathers petabytes of data from those millions of client devices and thousands of access points, and first establishes a baseline. How well does the network perform, in terms of things such as what percentage of users have a wireless connection issue, on average, or what percentage have a Citrix application connectivity issue? Some of these devices have no users, they are Internet-of-Things gadgets, such as a General Electric wireless patient monitor, or the wrenches used by Tesla on the shop floor in its Fremont facility. Telemetry data must be gathered from those devices as a baseline for performance.


Nyansa, a network monitoring startup competing with Cisco and Hewlett-Packard Enterprise, believes it wins the day for clients such as Uber not by the complexity of its artificial intelligence tools, which are fairly routine, but by its understanding of the problem of network performance. (Image: Nyansa)

“One way you can think of us is as a vertically-integrated Splunk,” says Srinivas, referring to the Big Data monitoring system that ingests and mines customer data. “We can take any type of data and tie it into our system, but we go one step further to solve customer use cases.”

Also: Cisco launches UCS system for AI, machine learning, deep learning

By having data from multiple customers in the cloud, says Srinivas, a baseline can be set not just for a given customer but across an industry. “What’s good performance,” he asks rhetorically. For a given industry, “if the baseline is a 30 percent network performance connection failure, then 5 percent for a given customer may be fine for them.”

Once a baseline is established, deviations can be detected in order to determine if a problem is, say, a network problem per se, or rather an application problem. And once deviations from the baseline are established, predictions can be made. “Based on what other customers have done, what is our prediction for actions that have been most beneficial,” is how he describes it. By then observing how recommendations are carried out, and the effects, the system can move beyond mere correlation, the focus of a lot of machine learning, to a sense of causality.

“By automatically learning a baseline, and learning it everywhere, and doing it in the exact same way, we can give you a recommendation, and it will have an impact.”

“At first, perhaps it’s 80 percent correlation. But when a customer takes that action, that baseline will tell you the truth of whether the action made a difference; if it [performance] gets better, the recommendation by definition is correct. That feedback loop gets you back into causation.”

Also: Why you need to learn about application performance monitoring TechRepublic

As to how they differ from Cisco or Hewlett, Srinivas sees the Nyansa system as more comprehensive in what it looks at than either one. “We don’t care who the vendor is for wireless [access points] or RADIUS or DNS or DHCP, we will take whatever data from whatever source, that is a fundamental difference.”

“Their data sources are limited to their own stuff.”

Srinivas offers the example of GE bedside wireless patient monitors in a hospital run by client Mission Health, a healthcare system serving North Carolina. It is not enough to say that a network is or is not performing at baseline. “The final thing that matters is, are those waveforms [of patient data from the monitors] getting back to the nurse, and is that nurse able to see the oxygen level on the screen. It doesn’t matter if the wireless signal is good, you can’t just baseline wireless, because the particular data source you care about, the monitor, has nothing to do with switches.”

Also: Facebook is using AI to curb exploitative and naked images of kids CNET

The answer, then, to machine learning, in its simpler form and perhaps even its more complex incarnations, is how engaging with the complexity of situations builds understanding. “Even with deep learning, the magic is in tuning the deep learning network, knowing how to turn the knobs,” observes Srinivas. “The crux of it is experience, over time knowing exactly how to tune things.”

Previous and related coverage:

What is AI? Everything you need to know

An executive guide to artificial intelligence, from machine learning and general AI to neural networks.

What is deep learning? Everything you need to know

The lowdown on deep learning: from how it relates to the wider field of machine learning through to how to get started with it.

What is machine learning? Everything you need to know

This guide explains what machine learning is, how it is related to artificial intelligence, how it works and why it matters.

What is cloud computing? Everything you need to know about

An introduction to cloud computing right from the basics up to IaaS and PaaS, hybrid, public, and private cloud.

Related stories:

Source link

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Cars

Mini John Cooper Works convertible and coupe pack style and performance

Published

on

Mini has unveiled its convertible and coupe John Cooper Works sports cars. The hardtop is rated for a combined fuel economy of 7.1-6.8 l/100 km, with the convertible rated for 7.4-7.1 l/100 km. The vehicles also have low CO2 emissions making them sporty, fun to drive, and green. Mini said that the cars have fresh design features and new equipment for the current year model.

Both versions of the John Cooper Works have round LED headlights and a larger hexagonal radiator grille. The larger radiator grille works with larger side openings to channel more cooling air to the drivetrain and brakes. Mini also paints the bumper strip in body color and has modified the side scuttles on the front side panels and the rear diffuser on both models.

Power comes from a 2.0-liter four-cylinder engine with TwinPower turbo technology. The engine produces 231 horsepower and 320Nm of torque. The car can reach 100 km/h in 6.3 seconds in hardtop form when fitted with the standard six-speed manual transmission. When fitted with the optional eight-speed Steptronic Sport transmission, the vehicle can reach the same speed in 6.1 seconds.

The convertible is a little slower to 100 km/h needing 6.6 seconds with the manual and 6.5 seconds with the automatic. Buyers of the convertible get an electrically powered textile soft top and can choose an optional Mini Yours soft top with woven in Union Jack graphics. The top can be opened at speeds up to 30 km/h.

Both models feature Brembo brakes and 17-inch wheels; 18-inch wheels are an option. The latest version of the optional Adaptive Suspension is available to provide a balance between sportiness and ride comfort. The car also gets standard heated steering well, lane departure warning, and stop & go function for the active cruise control. An 8.8-inch touch display is used for the infotainment system. Pricing for both models is unannounced at this time.

Continue Reading

Cars

Opel Manta GSe ElektroMOD teases innovative Pixel-Vizor front grille

Published

on

Last March, Opel gave us a teaser of its latest Manta GSe ElektroMOD concept, an all-electric version of the brand’s popular sports coupe from the 1970s. The German carmaker is back to reveal more about its latest electric restomod, notably its unique Pixel-Vizor front grille that allows the car (and driver) to send animated messages to other road users.

“The Manta GSe ElektroMOD is the work of passionate designers, 3D modelers, engineers, technicians, mechanics, product and brand experts,” said Pierre-Olivier Garcia, Opel Global Brand Design Manager. “With the Manta GSe, we are building a bridge from the great Opel tradition to a very desirable sustainable future. This mixture of zeitgeist and modern is absolutely fascinating.”

Other EVs like the Mustang Mach-E and Kia EV6 have blanked-out grille designs, while others have illuminated units. Opel’s Pixel-Vizor front grille takes it further. It’s a digital screen spanning across the entire front of the vehicle. It can display a bevy of messages to communicate with pedestrians, onlookers, and other cars on the road.

In Opel’s video, you can see the car displaying “My German heart has been ELEKTRified,” “I am an ElektroMOD,” and “I am on a zero e-mission.” You can also see an animated manta ray gliding over the screen between the headlights. Yes, we’re talking about a concept vehicle, but we can’t see any reason why this feature won’t make it to production.

Opel utilized a Manta A model from its classic warehouse in creating the GSe ElektroMOD. If you’re old enough to remember, the original Manta was an iconic sports coupe with twin round headlights, a Hemi Cuda-esque hood, and a sporty two-door coupe silhouette.

Opel’s first electric car, the Elektro GT, debuted at the Frankfurt Motor Show in 1971 and is based on the Opel GT sports car from 1968. It came with a pair of Bosch electric motors and an all-electric range of only 27 miles. Despite this, it rockets from zero to 60 mph in under six seconds, pretty quick even by modern standards.

As you can see, Opel’s been dabbling with electrification since the early 70s, and it seems the incoming Manta GSe ElektroMOD is bridging the gap between the old and the new. We have no idea if this electric Manta is entering production, but there’s a glimmer of hope.

According to Opel, the Manta GSe ElektroMOD is getting its final touches at the company HQ in Rüsselsheim, Germany. It will also reveal the concept in all its glory this May 19, 2021. Until then, we’ll be back to share the deets.

Continue Reading

Cars

Ferrari 812 Superfast Versione Speciale has the most potent Ferrari V12 engine

Published

on

As the name suggests, a standard Ferrari 812 Superfast is, well, a stupendously quick supercar. However, Ferrari recently unveiled a ‘faster’ and more potent version of the 812 Superfast. It will debut on May 5 as having the most powerful and highest-revving V12 engine in Ferrari’s history.

Ferrari refers to it as Versione Speciale or Special Version, although the name might change upon the vehicle’s debut in the next couple of weeks. Despite this, Ferrari was able to whet our appetites by releasing a couple of tidbits about its latest high-speed creation.

The Versione Speciale will have the same 6.5-liter V12 engine as a standard 812 Superfast. However, it now pumps out an astonishing 830 horsepower, 30+ more horses than stock. It has the same power output as Mansory’s Stallone GTS convertible (a highly-tuned version of the 812 Superfast), and we reckon it’s going to just as quick.

Officially, the 812 Versione Speciale’s V12 is the most powerful gasoline engine in a roadgoing Ferrari. Granted, the Ferrari SF90 Stradale and Spider have 986 horsepower from a 4.0-liter twin-turbo V8, but the SF90 is a hybrid.

The new V12 also revs with authority, spinning close to 9,500 rpm. Considering a stock 812 Superfast produces maximum power at 8,500 rpm, we’re pretty sure the Special Version will sound more epic at full chat. Ferrari failed to mention the torque numbers, but we expect the new V12 to have more twists than a stock motor’s 530 pound-feet output.

We have no word yet on the performance numbers. But with more power than stock, the Ferrari 812 Superfast Versione Speciale will go like stink. A standard 812 Superfast goes from zero to 60 mph in 2.9-seconds, zero to 124 mph in 7.9-seconds, and has a top speed of 211 mph. Meanwhile, the Mansory Stallone GTS accelerates to 60 mph in 2.8-seconds and has a top speed of 214 mph, all while having the same power output as Ferrari’s latest 812 VS.

Other juicy features include Ferrari’s Slide Slip Control vehicle dynamics system and four-wheel steering for better handling. The exterior mods consist of more oversized air intakes, a new lip spoiler, new bumper fins, and an aluminum lover panel covering the rear glass. We also heard it’ll weigh less than a stock Superfast, tipping the scales at under 3,362 pounds (1,525 kg).

We’ll know more about Ferrari’s most extreme version of the 812 Superfast in the coming weeks.

Continue Reading

Trending