INCORPORATING PRIOR KNOWLEDGE INTO TEMPORAL DIFFERENCE NETWORKS
نویسندگان
چکیده
منابع مشابه
Incorporating Prior Knowledge into Temporal difference Networks
Developing general purpose algorithms for learning an accurate model of dynamical systems from example traces of the system is still a challenging research problem. Predictive State Representation (PSR) models represent the state of a dynamical system as a set of predictions about future events. Our work focuses on improving Temporal Difference Networks (TD Nets), a general class of predictive ...
متن کاملIncorporating Prior Knowledge into
We describe a modiication to the AdaBoost algorithm that permits the incorporation of prior human knowledge as a means of compensating for a shortage of training data. We give a convergence result for the algorithm. We describe experiments on four datasets showing that prior knowledge can substantially improve performance.
متن کاملIncorporating Prior Knowledge on Features into Learning
In the standard formulation of supervised learning the input is represented as a vector of features. However, in most real-life problems, we also have additional information about each of the features. This information can be represented as a set of properties, referred to as meta-features. For instance, in an image recognition task, where the features are pixels, the meta-features can be the (...
متن کاملIncorporating prior knowledge into image registration.
The first step in the spatial normalization of brain images is usually to determine the affine transformation that best maps the image to a template image in a standard space. We have developed a rapid and automatic method for performing this registration, which uses a Bayesian scheme to incorporate prior knowledge of the variability in the shape and size of heads. We compared affine registrati...
متن کاملIncorporating Prior Knowledge into Gaussian Process Models
Gaussian processes (GP) models form an emerging methodology for modelling nonlinear dynamic systems which tries to overcome certain limitations inherent to traditional methods such as e.g. neural networks, fuzzy models or local model networks. The GP model seems promising for three reasons — first, smaller number of training parameters, second, the variance of model’s output is automatically ob...
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 Computer Science
سال: 2014
ISSN: 1549-3636
DOI: 10.3844/jcssp.2014.2211.2219