Apprentissage de séquences et extraction de règles de réseaux récurrents : application au traçage de schémas techniques

mars 2018

Directeur(s) de thèse : Frédéric Alexandre et Nicolas Rougier, Equipe Mnemosyne, INRIA

Résumé de thèse

Implicit knowledge is acquired in two ways. The first consists in the repetition of sequences, which allows the individual to extract implicitly regularities. The second way is a migration of explicit knowledge into implicit knowledge during the development of an expertise. In both cases, it is implicit learning.
In our work, we endeavor to observe sequences of electrical components and in particular the problem of extracting rules hidden in these sequences, which are an important aspect of the extraction of business expertise from technical drawings.
We place ourselves in the connectionist domain, and we have particularly considered neuronal models capable of processing sequences. We implemented two recurrent neural networks: the Elman model and a model with LSTM (Long Short Term Memory) units. We have evaluated these two models on different artificial grammars (Reber’s grammar and its variations) in terms of learning, their generalization abilities and their management of sequential dependencies.
Finally, we have also shown that it is possible to extract the encoded rules (from the sequences) in the recurrent network with LSTM units, in the form of an automaton.
The electrical domain is particularly relevant for this problem. It is more constrained with a limited combinatorics than the planning of tasks in general cases like navigation for example, which could constitute a perspective of this work.

Mots clés : Recurrent Neural Networks, LSTM, Sequence Learning, Rules Extraction, Technical diagrams