Simone Marullo

PhD Student @ SAILAB | Interested in AI, Machine Learning and Continual Learning

[Matteo Tiezzi @TiezziMatteo]

It has been amazing to have been back to a physical @IJCAIconf #IJCAI2022 together with @enricomeloni_ai and @MarulloSimone‼️
"Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams" proceedings: https://t.co/P76TXP32Nq

[CLiC-it Conference @CLiC_it_conf]

Exploitation of language neural representations for the retrieval and ranking of crossword clues and answers presented by @AZugarini
https://t.co/2EVZaPwTof #clicit2021 #NLProc @AILC_NLP

[Matteo Tiezzi @TiezziMatteo]

#IJCAI2022
"Stochastic Coherence Over Attention Trajectory
For Continuous Learning In Video Streams"
by @TiezziMatteo, @MarulloSimone, Lapo Faggi, @enricomeloni_ai, @aleitteb and
@StefanoMelacci.
Soon @IJCAIconf ‼️
Technical report: https://t.co/cotr3ocTDz

7/7

[Matteo Tiezzi @TiezziMatteo]

Thanks to #NFT, noisy information can be discarded. We introduced some noise in #CIFAR10 dataset. #NFT foster the standard training process (CT) of a ResNet18. A work by @MarulloSimone , @TiezziMatteo , @KleineBottleM , @StefanoMelacci. Soon #AAAI2022 ! https://t.co/2sr5PvhZfG

[Matteo Tiezzi @TiezziMatteo]

In Neural Friendly Training (#NFT 🐵), we show that major improvements can be obtained by introducing a temporary auxiliary neural model implementing a structured and shared transformation function - to spot regularities in the data alteration process https://t.co/2sr5PvhZfG

[Matteo Tiezzi @TiezziMatteo]

Friendly Training (FT) alter the training data to facilitate the learning process of a neural classifier. Transformations discard the parts of information that are too complex to be handled by the network with the current weights. https://t.co/8CDpWzJkxA

[Matteo Tiezzi @TiezziMatteo]

In Adversarial Machine Learning, Neural models alter data samples, aimed at fooling a classifier. Why not be a friend? "Being Friends Instead of Adversaries: Deep Networks Learn from Data Simplified by Other Networks" #AAAI22 @RealAAAI! https://t.co/2sr5PvhZfG 👇🧵

[DeepAI @DeepAI]

Friendly Training: Neural Networks Can Adapt Data To Make Learning Easier
https://t.co/RbUdyQbOJX
by Simone Marullo et al. including @TiezziMatteo
#DeepLearning #NeuralNetwork