Machine Learning

Texas Instruments
edgeai_blog_1920x1080
Learning Resources

Creating Smarter, More Efficient Solutions Through Edge AI

Sponsored by Texas Instruments: Integrating AI into devices on the edge can be simplified with NPU-enhanced MCUs and having the right tools at your fingertips.
Alpha and Omega Semiconductor (generated by AI)
241220_prodmod_alphaomega_ai_pwm_controller
Power

PWM Controller Tailored for AI Server and Graphics Cards Based on Blackwell GPUs

The four-phase PWM controller pairing with Alpha and Omega’s benchmark DrMOS exhibits the best system efficiency for NVIDIA’s Blackwell GPU platforms.
ID 130409802 © Funtap P | Dreamstime.com
ai_dreamstime_l_130409802
EDA

Production-Grade AI Arrives in EDA for Analog Design and Verification

Unlocking the future of analog design, AI-driven verification accelerates innovation by breaking through traditional SPICE bottlenecks, ensuring faster, more accurate results....
Dreamstime_tondone_326165096
ed_survey_dreamstime_tondone_326165096_promo
Industry Insights

How is Artificial Intelligence Affecting Your Job?

In our salary survey, we posed questions to our readers on the ways artificial intelligence may be impacting their profession.
ID 321264446 © Studioclever | Dreamstime.com
Generative AI in the data center
Nonlinearities

Could Sagence AI’s Analog Inferencing for GenAI be NVIDIA’s Downfall?

AI data centers typically require hundreds of megawatts of power, and it continues to rise to the point where most power companies refuse to provide such capacity from the public...
Dreamstime_alenabutusava_316508515
dreamstime_alenabutusava_316508515
Inside Electronics

Practical Spiking Neural Networks

BrainChip’s Steve Brightfield talks about efficient neuromorphic computing via SNNs.
Dreamstime_davinci_153429135
robot_dreamstime_davinci_153429135
Nonlinearities

So...AI is Worse than a 3rd Grader in Understanding Language Dialects

Our intrepid, mostly analog editor takes a stab at AI and then tries translating a recent Electronic Design product writeup from Pirate-speak to plain English.
Neuromorphic NPU Sips Power to Handle ML on the Edge
Machine Learning

Neuromorphic NPU Sips Power to Handle Edge Machine-Learning Models

BrainChip’s Akida Pico neural processing unit, which leverages spiking neural networks, targets low-power IoT and edge-computing devices.
ThinkStock
promo__eta_compute__thinkstock
TechXchange

Edge Computing and TinyML

Edge computing often had limited power, and compute resources for machine-learning support needs to fit within these constraints.