#edge-devices

[ follow ]
#hailo
TechCrunch
3 months ago
Artificial intelligence

Hailo lands $120 million to keep battling Nvidia as most AI chip startups struggle | TechCrunch

Funding for AI chip startups is declining due to Nvidia's dominance
Hailo, a startup specializing in AI chips for edge devices, has found success with over 300 customers [ more ]
TechCrunch
1 month ago
Artificial intelligence

Raspberry Pi partners with Hailo for its AI extension kit | TechCrunch

Raspberry Pi 5 now offers AI capabilities with an AI Kit extension featuring an M.2 slot and Hailo-8L accelerator module for enhanced inferencing performance. [ more ]
TechCrunch
3 months ago
Artificial intelligence

Hailo lands $120 million to keep battling Nvidia as most AI chip startups struggle | TechCrunch

Funding for AI chip startups is declining due to Nvidia's dominance
Hailo, a startup specializing in AI chips for edge devices, has found success with over 300 customers [ more ]
TechCrunch
1 month ago
Artificial intelligence

Raspberry Pi partners with Hailo for its AI extension kit | TechCrunch

Raspberry Pi 5 now offers AI capabilities with an AI Kit extension featuring an M.2 slot and Hailo-8L accelerator module for enhanced inferencing performance. [ more ]
morehailo
#deep-learning models
MIT News | Massachusetts Institute of Technology
7 months ago
Artificial intelligence

Technique enables AI on edge devices to keep learning over time

Personalized deep-learning models can be trained on edge devices, eliminating the need to transmit sensitive user data to cloud servers.
PockEngine, a new on-device training method, enables fine-tuning of machine learning models directly on edge devices, improving privacy and reducing computational overhead.
PockEngine significantly speeds up on-device training, performing up to 15 times faster on some hardware platforms, without compromising accuracy. [ more ]
MIT News | Massachusetts Institute of Technology
7 months ago
Artificial intelligence

Technique enables AI on edge devices to keep learning over time

Personalized deep-learning models can be trained on edge devices, eliminating the need to transmit sensitive user data to cloud servers.
PockEngine, a new on-device training method, enables fine-tuning of machine learning models directly on edge devices, improving privacy and reducing computational overhead.
PockEngine significantly speeds up on-device training, performing up to 15 times faster on some hardware platforms, without compromising accuracy. [ more ]
MIT News | Massachusetts Institute of Technology
7 months ago
Artificial intelligence

Technique enables AI on edge devices to keep learning over time

Personalized deep-learning models can be trained on edge devices, eliminating the need to transmit sensitive user data to cloud servers.
PockEngine, a new on-device training method, enables fine-tuning of machine learning models directly on edge devices, improving privacy and reducing computational overhead.
PockEngine significantly speeds up on-device training, performing up to 15 times faster on some hardware platforms, without compromising accuracy. [ more ]
MIT News | Massachusetts Institute of Technology
7 months ago
Artificial intelligence

Technique enables AI on edge devices to keep learning over time

Personalized deep-learning models can be trained on edge devices, eliminating the need to transmit sensitive user data to cloud servers.
PockEngine, a new on-device training method, enables fine-tuning of machine learning models directly on edge devices, improving privacy and reducing computational overhead.
PockEngine significantly speeds up on-device training, performing up to 15 times faster on some hardware platforms, without compromising accuracy. [ more ]
moredeep-learning models
TNW | Deep-Tech
1 week ago
Artificial intelligence

Samsung backs 'world's most powerful' AI chip for edge devices

Axelera raised $68mn with lead investor Samsung Catalyst, aims to make AI chips for edge devices using in-memory computing. [ more ]
InfoQ
3 weeks ago
DevOps

Microsoft Enhances Azure Monitor with Query Editor and Support for PromQL

Users can now create and run PromQL queries within Azure Monitor Metrics, enhancing productivity and streamlining metrics analysis. [ more ]
[ Load more ]