8 papers
RCNet: IADCs as Recurrent AutoEncoders
Arnaud Verdant, William Guicquero, Jérôme Chossat
This paper proposes a deep learning model (RCNet) for Delta-Sigma () ADCs. Recurrent Neural Networks (RNNs) allow to describe both modulators and filters. This analogy is app…
End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning
Thien Nguyen, William Guicquero
Existing works on Binary Neural Network (BNN) mainly focus on model's weights and activations while discarding considerations on the input raw data. This article introduces Generic…
Generative Binary Memory: Pseudo-Replay Class-Incremental Learning on Binarized Embeddings
Yanis Basso-Bert, Anca Molnos, Romain Lemaire +2
In dynamic environments where new concepts continuously emerge, Deep Neural Networks (DNNs) must adapt by learning new classes while retaining previously acquired ones. This challe…
Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networks
Yanis Basso-Bert, Anca Molnos, Romain Lemaire +2
Binary Neural Networks (BNNs) are a promising approach to enable Artificial Neural Network (ANN) implementation on ultra-low power edge devices. Such devices may compute data in hi…
BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference
Van Thien Nguyen, William Guicquero, Gilles Sicard
Long Short-Term Memory (LSTM) and 3D convolution (Conv3D) show impressive results for many video-based applications but require large memory and intensive computing. Motivated by r…
MOGNET: A Mux-residual quantized Network leveraging Online-Generated weights
Van Thien Nguyen, William Guicquero, Gilles Sicard
This paper presents a compact model architecture called MOGNET, compatible with a resource-limited hardware. MOGNET uses a streamlined Convolutional factorization block based on a…