MicroAI is a software framework for end-to-end deep neural networks training, quantization and deployment onto embedded devices. This framework is designed as an alternative to existing proprietary inference engines on microcontrollers. Our framework can be easily adjusted and/or extended for specific use cases. The training phase relies on Keras or PyTorch. Execution using single precision 32-bit floating-point as well as fixed-point on 8- and 16 bits integers are supported. https://bitbucket.org/edge-team-leat/uca-eharhttps://bitbucket.org/edge-team-leat/microai_publi
Narrow bit-width data formats are key to reducing the computational and storage costs of modern deep...
Deep Learning is moving to edge devices, ushering in a new age of distributed Artificial Intelligenc...
International audienceThe ever-growing cost of both training and inference for state-of-the-art neur...
International audienceEmbedding Artificial Intelligence onto low-power devices is a challenging task...
In recent years, machine learning has very much been a prominent talking point, and is considered by...
With the surge of inexpensive computational and memory resources, neural networks (NNs) have experie...
There is great potential in enabling neural network applications in embedded devices and an importan...
Next generation of embedded Information and Communication Technology (ICT) systems are interconnecte...
Differently to the common belief, the industry quest for ultra-low-power neural networks is just at ...
Next generation of embedded Information and Communication Technology (ICT) systems are interconnecte...
Next generation of embedded Information and Communication Technology (ICT) systems are interconnecte...
The creation of effective computational models that function within the power limitations of edge de...
We introduce Neuro.ZERO-a co-processor architecture consisting of a main microcontroller (MCU) that ...
Narrow bit-width data formats are key to reducing the computational and storage costs of modern deep...
Deep Learning is moving to edge devices, ushering in a new age of distributed Artificial Intelligenc...
International audienceThe ever-growing cost of both training and inference for state-of-the-art neur...
International audienceEmbedding Artificial Intelligence onto low-power devices is a challenging task...
In recent years, machine learning has very much been a prominent talking point, and is considered by...
With the surge of inexpensive computational and memory resources, neural networks (NNs) have experie...
There is great potential in enabling neural network applications in embedded devices and an importan...
Next generation of embedded Information and Communication Technology (ICT) systems are interconnecte...
Differently to the common belief, the industry quest for ultra-low-power neural networks is just at ...
Next generation of embedded Information and Communication Technology (ICT) systems are interconnecte...
Next generation of embedded Information and Communication Technology (ICT) systems are interconnecte...
The creation of effective computational models that function within the power limitations of edge de...
We introduce Neuro.ZERO-a co-processor architecture consisting of a main microcontroller (MCU) that ...
Narrow bit-width data formats are key to reducing the computational and storage costs of modern deep...
Deep Learning is moving to edge devices, ushering in a new age of distributed Artificial Intelligenc...
International audienceThe ever-growing cost of both training and inference for state-of-the-art neur...