Hierarchical Neural Networks
July 15, 2016
The German Traffic Sign Benchmark actually has the signs divided into groups: speed limits, danger signs, and so on. It turns out that humans make far fewer errors between groups than within groups. They might mistake a 30kph speed limit sign for an 80kph sign, but very rarely for a stop sign. The errors CNNs make are much less structured and are pretty much all over the place, so there is clearly room for improvement. How can we teach CNNs to be more like humans?
To read the full article, click here
Related Semiconductor IP
- Highly scalable performance for classic and generative on-device and edge AI solutions
- MIPI CSI-2 TX Controller
- 1.6T Ultra Ethernet Controller
- HBM4E PHY and controller
- DDR5 MRDIMM PHY and Controller
Related Blogs
- Embedded Vision: The Road Ahead for Neural Networks and Five Likely Surprises
- Push-button generation of deep neural networks
- Deployable Artificial Neural Networks Will Change Everything
- Neural Networks and the Future
Latest Blogs
- From AI-Assisted EDA to AI-Mediated Engineering
- Simplifying Multi-Domain Voltage-Control Verification with Synopsys AVSBus 2.0 VIP
- The Cyber Resilience Act Is Turning Hardware Security into an Evidence Question
- Inside the Arm Mali G2-Ultra NX GPU: Delivering desktop-class mobile gameplay with AI-native graphics
- Synopsys Joins Arm Total Design for Physical AI to Advance Autonomous Systems