All About Circuits

Latest AI/Neural Networks Articles and Videos

Categories

CES Memory Roundup: Companies Tackle Bandwidth, Power, and Reliability

CES Memory Roundup: Companies Tackle Bandwidth, Power, and Reliability

Gen5 QLC client SSDs, enterprise LPDDR5X with RAIDDR ECC, and HBM4-era AI memory concepts anchor a week of announcements.


News Jan 21, 2026 by Luke James
Cadence Unwraps DSP IP Purpose-Built for Next-Gen Voice AI and Audio

Cadence Unwraps DSP IP Purpose-Built for Next-Gen Voice AI and Audio

Announced today, Cadence's new Tensilica HiFi iQ DSP doubles compute, octuples AI performance, and cuts power by 25% over its predecessor, targeting next-gen AI-voice and immersive automotive audio.


News Jan 21, 2026 by Duane Benson
How Brain-Inspired Hardware Is Learning to Scale

How Brain-Inspired Hardware Is Learning to Scale

While brain-inspired computing and neural interfaces have long promised transformative advances, scaling those systems has remained a challenge. New research suggests that the barrier is beginning to fall.


News Jan 20, 2026 by Austin Futrell
Voyant Photonics Has Silicon That Will ‘Make LiDAR as Common as Cameras’

Voyant Photonics Has Silicon That Will ‘Make LiDAR as Common as Cameras’

At CES, All About Circuits interviewed Voyant Photonics' CEO to learn about the company's vision for LiDAR's camera-like future with solid-state 4D FMCW sensing.


News Jan 19, 2026 by Jake Hertz
TDK Merges Sensing and Intelligence at the Edge Like Never Before

TDK Merges Sensing and Intelligence at the Edge Like Never Before

All About Circuits met with TDK at CES 2026 to learn how their solutions may redefine sensing, inference, and context awareness in wearables and smart glasses.


News Jan 19, 2026 by Jake Hertz
Defending the Digital Highway: Cybersecurity for Software-Defined Vehicles

Defending the Digital Highway: Cybersecurity for Software-Defined Vehicles

Learn how evolving regulations, lifecycle security strategies, and quantum-ready cryptography are reshaping automotive cybersecurity.


Inside eMASS’s ECS-DoT SoC: Decompression and AI at the Sensor Edge

Inside eMASS’s ECS-DoT SoC: Decompression and AI at the Sensor Edge

In this exclusive CES interview, All About Circuits learned how EMASS's new ultra-low-power SoC brings intelligence where size, power, and latency matter most: the sensor edge.


News Jan 14, 2026 by Jake Hertz
Software-Defined Systems: Reshaping the Future of Modern Cars

Software-Defined Systems: Reshaping the Future of Modern Cars

This article explores how digital twins can help to reshape the design methodology of automotive semiconductors and systems, enabling truly software-defined vehicles.


For the First Time, AI Designs a Computer—in Less Than a Week

For the First Time, AI Designs a Computer—in Less Than a Week

Quilter has designed a fully functional Unix computer using AI, compressing a quarter's worth of PCB design time into a single week.


News Jan 14, 2026 by Arjun Nijhawan
Qualcomm Brings AI Compute to PCs, Robots, and Vehicles at CES

Qualcomm Brings AI Compute to PCs, Robots, and Vehicles at CES

Four CES announcements show Qualcomm pushing the same idea across categories: move more AI and control loops onto efficient, tightly integrated edge platforms.


News Jan 13, 2026 by Luke James
Texas Instruments Intros New SoC Family at CES to Scale Automotive AI

Texas Instruments Intros New SoC Family at CES to Scale Automotive AI

All About Circuits met with Texas Instruments at CES 2026 to learn about the company’s newest automotive SoCs.


News Jan 12, 2026 by Jake Hertz
Ceva Expands Edge AI Portfolio From Wearables to SDVs

Ceva Expands Edge AI Portfolio From Wearables to SDVs

At CES 2026, All About Circuits met with Ceva to learn about its latest hardware releases and collaborations driving the future of edge AI.


News Jan 12, 2026 by Jake Hertz
Broadcom Intros Wi-Fi 8 Chipset and AI Processor for Smart Homes

Broadcom Intros Wi-Fi 8 Chipset and AI Processor for Smart Homes

The new accelerated processing unit pairs with dual-band Wi-Fi 8 radios to deliver power-efficient, secure on-device AI inference to residential consumers.


News Jan 12, 2026 by Luke James
Exclusive—TSMC Enlightens Us About Its Next Steps in This Q&A

Exclusive—TSMC Enlightens Us About Its Next Steps in This Q&A

In this article, Gordon posed a set of questions to TSMC about their next steps going forward.


News Jan 09, 2026 by Gordon Feller
MIT Flips the Challenges of Chip Stacking On Its Head

MIT Flips the Challenges of Chip Stacking On Its Head

Low-temperature BEOL transistors and memory elements aim to cut data-movement energy in AI workloads.


News Jan 08, 2026 by Luke James
AI Chip Race Heats Up With Intel, Nvidia, and AMD’s CES Debuts

AI Chip Race Heats Up With Intel, Nvidia, and AMD’s CES Debuts

The industry's biggest chipmakers came to CES with processors that will shape the future of AI PCs, data center computing, and embedded AI.


News Jan 08, 2026 by Duane Benson
Design Wins: Four Designs Rethink Compute, Power, and Integration

Design Wins: Four Designs Rethink Compute, Power, and Integration

This four-product roundup highlights new hardware platforms for spaceborne AI, EV power, wireless sensing, and private 5G.


News Jan 07, 2026 by Joshua Tidwell
NXP Ushers Agentic AI to the Edge with New AI Development Tools

NXP Ushers Agentic AI to the Edge with New AI Development Tools

Announced today at CES, the new tools focus on inference-first deployment to embedded processors rather than retrofitting cloud-native workflows.


News Jan 06, 2026 by Jake Hertz
At CES, Ambarella Unwraps Edge AI 8K Vision SoC and New Developer Zone

At CES, Ambarella Unwraps Edge AI 8K Vision SoC and New Developer Zone

Today at CES, Ambarella unveiled an SoC with multi-sensor perception, multi-stream video, and very low power consumption.


News Jan 06, 2026 by Duane Benson
The New Moore’s Law: Why Optical Computing Could Redefine Scaling for AI

The New Moore’s Law: Why Optical Computing Could Redefine Scaling for AI

Optical computing is the "New Moore's Law" for AI. It solves electronic scaling limits, offering higher speed, lower power, and efficiency gains proportional to problem size for matrix operations.