-
The dynamics of learning with feedback alignment
Direct Feedback Alignment (DFA) is emerging as an efficient and biologic...
11/24/2020 ∙ by Maria Refinetti, et al. ∙
13
∙
share
read it
-
Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems
Scarcity of training data for task-oriented dialogue systems is a well k...
11/03/2020 ∙ by Stéphane d'Ascoli, et al. ∙
0
∙
share
read it
-
Triple descent and the two kinds of overfitting: Where why do they appear?
A recent line of research has highlighted the existence of a double desc...
06/05/2020 ∙ by Stéphane d'Ascoli, et al. ∙
19
∙
share
read it
-
Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime
Deep neural networks can achieve remarkable generalization performances ...
03/02/2020 ∙ by Stéphane d'Ascoli, et al. ∙
19
∙
share
read it
-
Conditioned Query Generation for Task-Oriented Dialogue Systems
Scarcity of training data for task-oriented dialogue systems is a well k...
11/09/2019 ∙ by Stéphane d'Ascoli, et al. ∙
7
∙
share
read it
-
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias
Despite the phenomenal success of deep neural networks in a broad range ...
06/16/2019 ∙ by Stéphane d'Ascoli, et al. ∙
0
∙
share
read it
-
Scaling description of generalization with number of parameters in deep learning
We provide a description for the evolution of the generalization perform...
01/06/2019 ∙ by Mario Geiger, et al. ∙
0
∙
share
read it
-
A jamming transition from under- to over-parametrization affects loss landscape and generalization
We argue that in fully-connected networks a phase transition delimits th...
10/22/2018 ∙ by Stefano Spigler, et al. ∙
0
∙
share
read it
-
The jamming transition as a paradigm to understand the loss landscape of deep neural networks
Deep learning has been immensely successful at a variety of tasks, rangi...
09/25/2018 ∙ by Mario Geiger, et al. ∙
0
∙
share
read it
