initial commit

Rapport/resources/bib/references.bib

@@ -0,0 +1,21 @@
+%%%
+% Utiliser BibTeX Tidy pour nettoyer les références bibliographiques
+% https://flamingtempura.github.io/bibtex-tidy/
+%%%
+
+@inproceedings{vaswaniAttentionAllYoua,
+	title        = {Attention Is {{All}} You {{Need}}},
+	author       = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
+	year         = 2017,
+	booktitle    = {Proceedings of the 31st International Conference on Neural Information Processing Systems},
+	location     = {Long Beach, California, USA},
+	publisher    = {Curran Associates Inc.},
+	address      = {Red Hook, NY, USA},
+	series       = {NIPS'17},
+	volume       = 30,
+	pages        = {6000–6010},
+	isbn         = 9781510860964,
+	abstract     = {The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles, by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.0 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature.},
+	numpages     = 11,
+	langid       = {english}
+}

Rapport/resources/gls/glossaire.tex

@@ -0,0 +1,45 @@
+%% Institutions
+
+\newglossaryentry{AID}{
+  type={institutions},
+  name={AID},
+  description={Agence de l'Innovation de Défense}
+}
+
+%% Plateformes matérielles
+
+\newglossaryentry{CPU}{
+  type={plateformes},
+  name={CPU},
+  description={Central Proccessing Unit}
+}
+\newglossaryentry{DLA}{
+  type={plateformes},
+  name={DLA},
+  description={Deep Learning Accelerator}
+}
+\newglossaryentry{GPU}{
+  type={plateformes},
+  name={GPU},
+  description={Graphics Proccessing Unit}
+}
+\newglossaryentry{FPGA}{
+  type={plateformes},
+  name={FPGA},
+  description={Field-Programmable Gate Array}
+}
+\newglossaryentry{PDU}{
+  type={plateformes},
+  name={PDU},
+  description={Power Distribution Unit}
+}
+\newglossaryentry{SoC}{
+  type={plateformes},
+  name={SoC},
+  description={System on Chip}
+}
+\newglossaryentry{TPU}{
+  type={plateformes},
+  name={TPU},
+  description={Tensor Proccessing Unit}
+}