EMBEDL TO DEVELOP NEXT-GENERATION EFFICIENT AI PLATFORM IN VEDLIOT Autonomous vehicles and devices for intelligent homes are becoming increasingly complex. These applications involve large collaborative systems which are powered by AI-based algorithms distributed...
Our Mission
We help customers build extraordinary
Deep Learning based products.
Accelerated
Time-to-Market
improved Product margins
Better Product Specifications
Value Added Partnership
product
Technology
Our award winning Deep Learning Optimization Engine optimizes your Deep Learning model for deployment (inference) to meet your requirements of:
- Execution Time (Latency)
- Throughput
- Runtime Memory Usage
- Power Consumption
EmbeDL enables you to deploy Deep Learning on less expensive hardware, using less energy and shorten the product development cycle.
EmbeDL interfaces with the commonly used Deep Learning development frameworks, e.g. Tensorflow and Pytorch. EmbeDL also have world leading support for hardware targets including CPUs, GPUs, FPGAs and ASICs from vendors like Nvidia, ARM, Intel and Xilinx.
We are happy to answer any questions and/or demonstrate EmbeDL on your Deep Learning model(s)!
benefits
FASTER
EXECUTION
By using state-of-the-art methods for optimizing Deep Neural Networks, we can achieve a significant decrease in execution time and help you reach your real time requirements.
SMALLER
FOOTPRINT IN DEVICE
The EmbeDL Optimization Engine automatically reduces the number of weights , and thus size of the model, to make it suitable to be deployed to resource constraint environments such as embedded systems
SHORTER
TIME-TO-MARKET
The tools are fully automatic, which reduces the need for time consuming experimentation and thus shorter time-to-market. It also frees up your data scientists to focus on their core problems.
LESS
ENERGY USAGE
Energy is a scarce resource in embedded systems and our optimizer can achieve an order of magnitude reduction in energy consumption for the Deep Learning model execution.
IMPROVED
PRODUCT MARGINS
By optimizing the Deep Learning model, cheaper hardware can be sourced that still meets your system requirements leading to improved product margins.
DECREASED
PROJECT RISK
Optimizing and deploying our customers’ Deep Learning models to embedded systems is what we do. By outsourcing this to us, your team can then focus on your core problems.
Partners and customers
Zenseact
(Volvo Cars)
Veoneer
Chalmers University
Bielefeld University
Technion – Israel Institute of Technology
Siemens
Christmann Informationstechnik
Barcelona Supercomputing Center
Osnabrück University
Research Institutes of Sweden
Antmicro
Maxeler Technologies
Gothenburg University
Neuchatel University
Technisch Universität Dresden
Networks
We are humbled to have been accepted into the following networks bringing together industry, academia and startups.
AWARDS
The EmbeDL Optimization Engine has received several awards for its technology and implementation.
Latest News
Latest Blog
The 4 main challenges of deploying deep learning
Are you experienced in making AI powered products or is this your first time on the deep learning carousel? Either way, you will face the same obstacles. No matter which hardware you are running on, there are always budget constraints to consider. Whether it´s a power budget, execution time budget or just a maximum cost for hardware that needs to be satisfied....
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 780681.
