Learning how to learn: Toddlers vs. neural networks
Gunn Salelanonda, CEVA
embedded.com (September 27, 2016)
It's undeniable that machine learning has made enormous progress over the past few years: from amazing artificial intelligence accomplishments like defeating a top ranking player at the ancient and complex game of Go, to simple everyday uses like auto-tagging personal photo collections. At the core of the most advanced algorithms used to achieve these feats are artificial neural networks, which are technology's way of mimicking the human brain. But just how smart are these neural networks? Since my not-quite-two-year-old son started paying attention to the world beyond his mom and started learning, I have been at awe by the way his brain learns by making associations; by comparison, I wonder how much further machine learning has to go.
To read the full article, click here
Related Semiconductor IP
- Tensilica ConnX 120 DSP
- CNN AI IP Core
- AI Accelerator Specifically for CNN
- Tensilica ConnX 110/120
- Tensilica ConnX B10/B20
Related Articles
- Wind Turbine Fault Detection Using Machine Learning And Neural Networks
- Machines can see, hear and analyze thanks to embedded neural networks
- Artificial Intelligence (AI) utilizing deep learning techniques to enhance ADAS
- ElfCore: A 28nm Neural Processor Enabling Dynamic Structured Sparse Training and Online Self-Supervised Learning with Activity-Dependent Weight Update
Latest Articles
- RISC-V Functional Safety for Autonomous Automotive Systems: An Analytical Framework and Research Roadmap for ML-Assisted Certification
- Emulation-based System-on-Chip Security Verification: Challenges and Opportunities
- A 129FPS Full HD Real-Time Accelerator for 3D Gaussian Splatting
- SkipOPU: An FPGA-based Overlay Processor for Large Language Models with Dynamically Allocated Computation
- TensorPool: A 3D-Stacked 8.4TFLOPS/4.3W Many-Core Domain-Specific Processor for AI-Native Radio Access Networks