The Boston Bruins were outplayed in every way in an ugly, blowout loss to the Carolina Hurricanes on Thursday night.

The Black and Gold not only lost 8-2 to the ‘Canes but they were also outshot 37-15 in the contest, managing just five shots on goal in each period.

Bruins head coach Jim Montgomery attempted to boost the offense by juggling all four forward lines, but Carolina’s puck pressure and pace were too much for Boston and the team couldn’t sustain any type of cohesiveness throughout the game.

“We knew they’d come hard,” Montgomery told Andy Brickley on NESN’s postgame coverage. “Unfortunately, we didn’t move pucks fast enough.”

David Pastrnak said the Bruins’ struggles are more than just line combinations not working.

“Right now, it’s not about the combinations,” he told reporters, as seen on NESN’s postgame coverage. “We are not good enough as a team, and that’s where it starts.”

Boston finished the first month of the season winning one game out of its last six, but Montgomery believes the team can turn it around in the upcoming month.

“We had a lot of success the last two years,” he said, per team-provided video. “We were first place in the league the last two years. We never achieved anything we wanted to.

“Right now, we’re not happy. Nobody’s happy with what’s going on. But we will get out of it. We will be better and hopefully create some better results come playoff time. It starts by sticking together and working. There’s no substitute for second and third effort.”

The Bruins aren’t willing to point the finger at any one player on the roster and are taking responsibility for how the team is playing on the ice.

“All you can do is keep working hard,” Trent Frederic told reporters, as seen on NESN’s postgame coverage. “I think everybody is doing that and trying their best. I think everyone needs to come together. A lot of individuals, including myself, aren’t doing well.

“I think everyone just needs to worry about the team and be team first. I’m not saying that’s the case, but the individual stuff will come and kind of all blend in together. We’ve done it for how many years now? It’s a recipe, we just got to get to it.”

More Bruins

One Big Takeaway From Bruins’ Unmitigated Ugly Loss Vs. Hurricanes

by Gayle Troiani
3 Min Read

Advertisement

Bruins Star Defends This Coaching Decision Following Dreadful Loss

by Gayle Troiani
3 Min Read

Advertisement

Here are more notes from Thursday’s Bruins-Hurricanes game:

— The Bruins’ 8-2 thrashing to Carolina is the worst loss for Boston since a 6-0 blowout defeat to the Hurricanes on Feb. 10, 2022, according to 98.5 The Sports Hub’s Ty Anderson.

— Boston surrendered three power-play goals for the third time this season in the first 11 games. The Bruins had allowed three power-play goals in a single game just three times in the previous 437 games, per Anderson.

— Brad Marchand tallied his second goal of the season and became the ninth player in franchise history to score 80 career power-play goals. The Bruins captain also moved into the fourth spot, ahead of Rick Middleton, in team history in goals scored (403).

— Jeremy Swayman was pulled midway through the second period after the Boston goaltender gave up six goals on 22 shots through 30 minutes.

— The Bruins travel to Philadelphia to take on the Flyers in a matinee matchup Saturday. Puck drop from Wells Fargo Center is slated for 1 p.m. ET. You can watch the game, plus an hour of pregame coverage, on NESN.

Dog-like robots could one day learn to play fetch, thanks to a blend of artificial intelligence (AI) and computer vision helping them zero in on objects.

In a new study published Oct.10 in the journal IEEE Robotics and Automation Letters, researchers developed a method called “Clio” that lets robots rapidly map a scene using on-body cameras and identify the parts that are most relevant to the task they’ve been assigned via voice instructions..

Clio harnesses the theory of “information bottleneck,” whereby information is compressed in a way so that a neural network — a collection of machine learning algorithms layered to mimic the way the human brain processes information — only picks out and stores relevant segments. Any robot equipped with the system will process instructions such as “get first aid kit” and then only interpret the parts of its immediate environment that are relevant to its tasks — ignoring everything else.

“For example, say there is a pile of books in the scene and my task is just to get the green book. In that case we push all this information about the scene through this bottleneck and end up with a cluster of segments that represent the green book,” study co-author Dominic Maggio, a graduate student at MIT, said in a statement. “All the other segments that are not relevant just get grouped in a cluster which we can simply remove. And we’re left with an object at the right granularity that is needed to support my task.”

‘Put glue on your pizza’ embodies everything wrong with AI search — is SearchGPT ready to change that?

To demonstrate Clio in action, the researchers used a Boston Dynamics Spot quadruped robot running Clio to explore an office building and carry out a set of tasks. Working in real time, Clio generated a virtual map showing only objects relevant to its tasks, which then enabled the Spot robot to complete its objectives.

Seeing, understanding, doing

The researchers achieved this level of granularity with Clio by combining large language models (LLMs) — multiple virtual neural networks that underpin artificial intelligence tools, systems and services — that have been trained to identify all manner of objects, with computer vision.

Neural networks have made significant advances in accurately identifying objects within local or virtual environments, but these are often carefully curated scenarios with a limited number of objects that a robot or AI system has been pre-trained to recognize. The breakthrough Clio offers is the ability to be granular with what it sees in real time, relevant to the specific tasks it’s been assigned.

A core part of this was to incorporate a mapping tool into Clio that enables it to split a scene into many small segments. A neural network then picks out segments that are semantically similar — meaning they serve the same intent or form similar objects.

Effectively, the idea is to have AI-powered robots that can make intuitive and discriminative task-centric decisions in real time, rather than try to process an entire scene or environment first.

In the future, the researchers plan to adapt Clio to handle higher-level tasks.

“We’re still giving Clio tasks that are somewhat specific, like ‘find deck of cards,’” Maggio said. “For search and rescue, you need to give it more high-level tasks, like ‘find survivors,’ or ‘get power back on.’” So, we want to get to a more human-level understanding of how to accomplish more complex tasks.”

If nothing else, Clio could be the key to having robot dogs that can actually play fetch — regardless of which park they are running around in.