English
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.
|
E-mail This Article | 
|
|
Printer-Friendly Page |
|
||||||
Ceva, Inc. Hot IP
Related Articles
- Wind Turbine Fault Detection Using Machine Learning And Neural Networks
- Neural Networks Can Help Keep Connected Vehicles Secure
- The realities of developing embedded neural networks
- Pyramid Vector Quantization and Bit Level Sparsity in Weights for Efficient Neural Networks Inference
- Machines can see, hear and analyze thanks to embedded neural networks
New Articles
- Accelerating RISC-V development with Tessent UltraSight-V
- Automotive Ethernet Security Using MACsec
- What is JESD204C? A quick glance at the standard
- Optimizing Power Efficiency in SOC with PVT Sensor-Assisted DVFS Technology
- Bandgap Reference (BGR) Circuit Design and Transient Analysis in 90nm VLSI Technology
Most Popular
- System Verilog Assertions Simplified
- Accelerating RISC-V development with Tessent UltraSight-V
- System Verilog Macro: A Powerful Feature for Design Verification Projects
- Understanding Logic Equivalence Check (LEC) Flow and Its Challenges and Proposed Solution
- Design Rule Checks (DRC) - A Practical View for 28nm Technology