Artificial Intelligence Applications in Consumer Electronic Devices
Artificial Intelligence Applications in Consumer Electronic Devices.
Topic 1: Machine Learning for Mobile Developers: Tensorflow Lite Framework (Avid Farhoodfar)
As Machine learning reaches the mainstream, new tools available to developers makes it possible to implement machine-learning features—voice, face, and image recognition; personalized recommendations; and more—in a mobile context.
With many model standards, such as Caffe, Keras, Scikit-learn and more, I'd like to focus our attention to TensorFlow Lite. TensorFlow Lite is a lightweight solution for mobile and embedded devices, derived from TensorFlow. It enables on-device machine learning inference with low latency and a small binary size. TensorFlow Lite also supports hardware acceleration with the Android Neural Networks API.
TensorFlow Lite applies many techniques for achieving low latency; optimizing the kernels for mobile apps, pre-fused activations, and quantized kernels that allow smaller and faster (fixed-point math) models.
Topic 2: Personal IoT Devices: Too much or much needed? (Zeki Gunay)
Abstract: Consumer demand is increasing for IoT products and some are entering our lives without us noticing. Where will consumer demand saturate for data and information?
In this presentation, Zeki will be presenting four products which CRATUS has developed which touch consumers and derive similarities and contrasts on use cases, value and we will collectively try to see the future of consumer IoT.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- 2800 Scott Blvd
- Santa Clara, California
- United States 95050
- Building: Nvidia Buliding E
- Click here for Map
- Contact Event Host
- Co-sponsored by ray.h@dracoelectronics.com
Speakers
Dr. Avid Farhoodfar
Machine Learning for Mobile Developers: Tensorflow Lite Framework
As Machine learning reaches the mainstream, new tools available to developers makes it possible to implement machine-learning features—voice, face, and image recognition; personalized recommendations; and more—in a mobile context.
With many model standards, such as Caffe, Keras, Scikit-learn and more, I'd like to focus our attention to TensorFlow Lite. TensorFlow Lite is a lightweight solution for mobile and embedded devices, derived from TensorFlow. It enables on-device machine learning inference with low latency and a small binary size. TensorFlow Lite also supports hardware acceleration with the Android Neural Networks API.
TensorFlow Lite applies many techniques for achieving low latency; optimizing the kernels for mobile apps, pre-fused activations, and quantized kernels that allow smaller and faster (fixed-point math) models.
Biography:
Avid Farhoodfar, PhD, is currently a Faculty in the Computer Science Department at Sofia University at Palo Alto, California. Formerly an Assistant chair in the Engineering Management Department, as well as Faculty in the Electrical and Computer Engineering Department at the International Technological University (ITU) in San Jose.
For her doctorate in Condensed Matter Physics and Material Sciences at Queen’s University, Dr. Farhoodfar modeled matter in quantum size, developing a modeling system using Quantum Monte Carlo approximation and Sherman Morrison optimization techniques.
Email:
Zeki Gunay
Personal IoT Devices: Too much or much needed?
Consumer demand is increasing for IoT products and some are entering our lives without us noticing. Where will consumer demand saturate for data and information?
In this presentation, Zeki will be presenting four products which CRATUS has developed which touch consumers and derive similarities and contrasts on use cases, value and we will collectively try to see the future of consumer IoT.
Biography:
Zeki is the founder and CEO of CRATUS Technology, a software platform company providing solutions for monitoring valuable, perishable and sensitive inventory and assets, whether portable or stationary, indoors or outdoors, in supply chain and logistics of BioPharma, F&B, aerospace, and several other markets. The platform combines sensor data, legacy barcodes, QR codes, NFC tags, microdisplays by mobile apps and gateways, cloud platform using edge computing and provides actionable information to ERP, supply chain or inventory management software. By using this system, companies see return in a short period by huge savings in operations.
Email:
Agenda
Avid Farhoodfar and Zeki Gunay will each present for 30 minutes followed by panel discussion facilitated by Dev Bhattacharya for 20 to 30 minutes