Theoretical learning guarantees applied to acoustic modeling
نویسندگان
چکیده
منابع مشابه
Providing theoretical learning guarantees to Deep Learning Networks
Deep Learning (DL) is one of the most common subjects when Machine Learning and Data Science approaches are considered. There are clearly two movements related to DL: the first aggregates researchers in quest to outperform other algorithms from literature, trying to win contests by considering often small decreases in the empirical risk; and the second investigates overfitting evidences, questi...
متن کاملFrom E-learning to Ubiquitous Learning; Theoretical Principles
Background: Because of approaches to learning in every place and at any time, ubiquitous learning with knowledge of the context and framework, and due to the development of wireless technologies and sensors, the learning process has changed. Mobile learning and ubiquitous learning as models of e-learning that refer to the acquisition of knowledge, attitudes and skills through wireless technolog...
متن کاملApplied Linguistic Approach to Language Learning Strategies (A Critical Review)
From applied linguistic point of view, the fundamental question facing the language teachers, methodologists and course designers is which procedure is more effective in FL/SL: learning to use or using to learn? Definitely, in order to be a competent language user, knowledge of language system is necessary, but it is not sufficient to be a successful language user. That is why there was a gradu...
متن کاملA discriminative decision tree learning approach to acoustic modeling
The decision tree is a popular method to accomplish tying of the states of a set context dependent phone HMMs for efficient and effective training of the large acoustic models. A likelihood-based impurity function is commonly adopted. It is well known that maximizing likelihood does not result in the maximal separation between the distributions in the leaves of the tree. To improve robustness, ...
متن کاملAdaptive neuro-fuzzy modeling applied to policy gradient reinforcement learning
-Function approximation has been used extensively with rein forcement learning, even though theoretical support was based mainly on tabular representations. This paper proposes an actor-critic structure following the existing convergence proofs as much as possible. The actor and critic modules employ an adaptive neuro-fuzzy architecture based on fuzzy ARTMAP concepts and gradient descent. Resul...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of the Brazilian Computer Society
سال: 2019
ISSN: 0104-6500,1678-4804
DOI: 10.1186/s13173-018-0081-3