The current trend for deep learning has come with an enormous computational need for billions of Multiply-Accumulate (MAC) operations per inference. Fortunately, reduced precision has demonstrated large benefits with low impact on accuracy, paving the way towards processing in mobile devices and IoT nodes. Precision-scalable MAC architectures optimized for neural networks have recently gained interest thanks to their subword parallel or bit-serial capabilities. Yet, it has been hard to make a fair judgment of their relative benefits as they have been implemented with different technologies and performance targets. In this work, run-time configurable MAC units from ISSCC 2017 and 2018 are implemented and compared objectively under diverse pr...
International audienceThis work deals with the optimization of Deep Convolutional Neural Networks (C...
Recently, there has been a push to perform deep learning (DL) computations on the edge rather than t...
Convolutional neural networks (CNNs) are one of the most successful machine-learning techniques for ...
The current trend for deep learning has come with an enormous computational need for billions of Mul...
As AI applications become more prevalent and powerful, the performance of deep learning neural netwo...
Deep Neural Networks (DNNs) computation-hungry algorithms demand hardware platforms capable of meeti...
Heavily quantized fixed-point arithmetic is becoming a common approach to deploy Convolutional Neura...
The deployment of Quantized Neural Networks (QNN) on advanced microcontrollers requires optimized so...
Recent success of machine learning in a broad spectrum of fields has awakened a new era of artificia...
Over the last ten years, the rise of deep learning has redefined the state-of-the-art in many comput...
International audienceThe most compute-intensive stage of deep neural network (DNN) training is matr...
As key building blocks for digital signal processing, image processing and deep learning etc, adders...
Brain-inspired computation promises a paradigm shift in information processing, both in terms of its...
Due to their potential to reduce silicon area or boost throughput, low-precision computations were w...
Hardware implementations of Artificial Neural Network (ANN) architectures cantake advantage of paral...
International audienceThis work deals with the optimization of Deep Convolutional Neural Networks (C...
Recently, there has been a push to perform deep learning (DL) computations on the edge rather than t...
Convolutional neural networks (CNNs) are one of the most successful machine-learning techniques for ...
The current trend for deep learning has come with an enormous computational need for billions of Mul...
As AI applications become more prevalent and powerful, the performance of deep learning neural netwo...
Deep Neural Networks (DNNs) computation-hungry algorithms demand hardware platforms capable of meeti...
Heavily quantized fixed-point arithmetic is becoming a common approach to deploy Convolutional Neura...
The deployment of Quantized Neural Networks (QNN) on advanced microcontrollers requires optimized so...
Recent success of machine learning in a broad spectrum of fields has awakened a new era of artificia...
Over the last ten years, the rise of deep learning has redefined the state-of-the-art in many comput...
International audienceThe most compute-intensive stage of deep neural network (DNN) training is matr...
As key building blocks for digital signal processing, image processing and deep learning etc, adders...
Brain-inspired computation promises a paradigm shift in information processing, both in terms of its...
Due to their potential to reduce silicon area or boost throughput, low-precision computations were w...
Hardware implementations of Artificial Neural Network (ANN) architectures cantake advantage of paral...
International audienceThis work deals with the optimization of Deep Convolutional Neural Networks (C...
Recently, there has been a push to perform deep learning (DL) computations on the edge rather than t...
Convolutional neural networks (CNNs) are one of the most successful machine-learning techniques for ...