no code implementations • 30 Mar 2024 • Taishi Nakamura, Mayank Mishra, Simone Tedeschi, Yekun Chai, Jason T Stillerman, Felix Friedrich, Prateek Yadav, Tanmay Laud, Vu Minh Chien, Terry Yue Zhuo, Diganta Misra, Ben Bogin, Xuan-Son Vu, Marzena Karpinska, Arnav Varma Dantuluri, Wojciech Kusa, Tommaso Furlanello, Rio Yokota, Niklas Muennighoff, Suhas Pai, Tosin Adewumi, Veronika Laippala, Xiaozhe Yao, Adalberto Junior, Alpay Ariyak, Aleksandr Drozd, Jordan Clive, Kshitij Gupta, Liangyu Chen, Qi Sun, Ken Tsui, Noah Persaud, Nour Fahmy, Tianlong Chen, Mohit Bansal, Nicolo Monti, Tai Dang, Ziyang Luo, Tien-Tung Bui, Roberto Navigli, Virendra Mehta, Matthew Blumberg, Victor May, Huu Nguyen, Sampo Pyysalo
Pretrained language models underpin several AI applications, but their high computational cost for training limits accessibility.
no code implementations • 25 Jun 2019 • Amy Zhang, Zachary C. Lipton, Luis Pineda, Kamyar Azizzadenesheli, Anima Anandkumar, Laurent Itti, Joelle Pineau, Tommaso Furlanello
In this paper, we propose an algorithm to approximate causal states, which are the coarsest partition of the joint history of actions and observations in partially-observable Markov decision processes (POMDP).
2 code implementations • ICML 2018 • Tommaso Furlanello, Zachary C. Lipton, Michael Tschannen, Laurent Itti, Anima Anandkumar
Knowledge distillation (KD) consists of transferring knowledge from one machine learning model (the teacher}) to another (the student).
no code implementations • ECCV 2018 • Yang Shi, Tommaso Furlanello, Sheng Zha, Animashree Anandkumar
Visual Question Answering (VQA) requires integration of feature maps with drastically different structures and focus of the correct regions.
no code implementations • ICLR 2018 • Jean Kossaifi, Zack Chase Lipton, Aran Khanna, Tommaso Furlanello, Anima Anandkumar
Second, we introduce tensor regression layers, which express the output of a neural network as a low-rank multi-linear mapping from a high-order activation tensor to the softmax layer.
no code implementations • 26 Jul 2017 • Jean Kossaifi, Zachary C. Lipton, Arinbjorn Kolbeinsson, Aran Khanna, Tommaso Furlanello, Anima Anandkumar
First, we introduce Tensor Contraction Layers (TCLs) that reduce the dimensionality of their input while preserving their multilinear structure using tensor contraction.
no code implementations • 20 Jun 2017 • Yang Shi, Tommaso Furlanello, Anima Anandkumar
Performing high level cognitive tasks requires the integration of feature maps with drastically different structure.
no code implementations • 1 Jun 2017 • Jean Kossaifi, Aran Khanna, Zachary C. Lipton, Tommaso Furlanello, Anima Anandkumar
Specifically, we propose the Tensor Contraction Layer (TCL), the first attempt to incorporate tensor contractions as end-to-end trainable neural network layers.
no code implementations • 7 Jun 2016 • Tommaso Furlanello, Jiaping Zhao, Andrew M. Saxe, Laurent Itti, Bosco S. Tjan
Continual Learning in artificial neural networks suffers from interference and forgetting when different tasks are learned sequentially.
no code implementations • 24 Oct 2013 • Tommaso Furlanello, Marco Cristoforetti, Cesare Furlanello, Giuseppe Jurman
The functional and structural representation of the brain as a complex network is marked by the fact that the comparison of noisy and intrinsically correlated high-dimensional structures between experimental conditions or groups shuns typical mass univariate methods.