Zobrazeno 1 - 10
of 773
pro vyhledávání: '"Schmidt, James A."'
Autor:
Schmidt, James
Empirical risk minimization stands behind most optimization in supervised machine learning. Under this scheme, labeled data is used to approximate an expected cost (risk), and a learning algorithm updates model-defining parameters in search of an emp
Externí odkaz:
http://arxiv.org/abs/2305.14606
Autor:
Schmidt, James
High complexity models are notorious in machine learning for overfitting, a phenomenon in which models well represent data but fail to generalize an underlying data generating process. A typical procedure for circumventing overfitting computes empiri
Externí odkaz:
http://arxiv.org/abs/2305.05792
Autor:
Schmidt, James
Stability is a fundamental notion in dynamical systems and control theory that, traditionally understood, describes asymptotic behavior of solutions around an equilibrium point. This notion may be characterized abstractly as continuity of a map assoc
Externí odkaz:
http://arxiv.org/abs/2304.07834
Creating artificial intelligence (AI) systems capable of demonstrating lifelong learning is a fundamental challenge, and many approaches and metrics have been proposed to analyze algorithmic properties. However, for existing lifelong learning metrics
Externí odkaz:
http://arxiv.org/abs/2207.14378
Autor:
Schmidt, James
This thesis (defended 10/07/2019) develops a theory of networks of hybrid open systems and morphisms. It builds upon a framework of networks of continuous-time open systems as product and interconnection. We work out categorical notions for hybrid sy
Externí odkaz:
http://arxiv.org/abs/1911.09048
We categorify the RK family of numerical integration methods (explicit and implicit). Namely we prove that if a pair of ODEs are related by an affine map then the corresponding discrete time dynamical systems are also related by the map. We show that
Externí odkaz:
http://arxiv.org/abs/1908.11453
Autor:
Lerman, Eugene, Schmidt, James
We generalize the results of "Networks of open systems" by the first author to the setting of hybrid systems. In particular we introduce the notions of hybrid open systems, their networks and maps between networks. A network of systems is a blueprint
Externí odkaz:
http://arxiv.org/abs/1908.10447
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Schmidt, James
In this thesis, we provide an initial investigation into bounds for topological entropy of switched linear systems. Entropy measures, roughly, the information needed to describe the behavior of a system with finite precision on finite time horizons,
Externí odkaz:
http://arxiv.org/abs/1610.02701