5 citations · 12 across the 8 of their papers we have counts for
5 papers · 1 filter
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…
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…
Histogram-Equalized Quantization for logic-gated Residual Neural Networks
Van Thien Nguyen, William Guicquero, Gilles Sicard
Adjusting the quantization according to the data or to the model loss seems mandatory to enable a high accuracy in the context of quantized neural networks. This work presents Hist…