As AI applications continue to proliferate and compute moves to the edge, companies are pressured to move quickly through the development and optimization process and deploy at lower and lower costs. In this session, we’ll explore how companies are decreasing […]
When developing an edge AI solution, DNN inference performance is critical: If your network doesn’t meet your throughput and latency requirements, you’re in trouble. But accurately measuring inference performance on target hardware can be time-consuming—just getting your hands on the […]
Have you ever been inspired by a new AI research paper and tried to replicate it using open source code, only to end up with a “bricked” development system? This is a common experience. The AI ecosystem is fragmented; many […]
As AI applications at the edge become pervasive, there’s growing interest in deploying AI on standard hardware platforms such as general-purpose CPUs. But are CPUs sufficient? In this roundtable discussion, we’ll explore the question: Does AI really require GPUs and […]
Solutions builders and business decision-makers designing edge AI computer vision systems should focus on five key factors to ensure outcomes that deliver ROI. The Five Rights of an edge AI computer vision system are streaming the right data, at the […]
New AI-at-the-edge processors with improved efficiencies and flexibility are unleashing a huge opportunity to democratize computer vision broadly across all markets, enabling edge AI devices with small, low-cost, low-power cameras. Synaptics has embarked on a roadmap of edge-AI DNN processors […]
This talk introduces a new method for object detection for consumer goods and other applications based on measuring an object’s illumination invariant fluorescent chroma. Chroma is a measure of the colorfulness of an object relative to a similarly illuminated white […]
Today’s face recognition networks identify white men correctly more often than white women or non-white people. The use of these models can manifest racism, sexism, and other troubling forms of discrimination. There are also publications suggesting that compressed models have […]
There are many statistical metrics used to measure the performance of machine learning models. While they work well when the model itself is the final product, classical measures are often not enough when the model is a part of a […]
The development of visual AI systems for real-world applications is a complex undertaking characterized by a variety of diverse challenges. While the media spotlight is often focused on academic AI models that improve performance based on well-defined datasets, in many […]
