User profiles for Ron Meir
Ron MeirProfessor of Electrical Engineeringe, Technion Verified email at ee.technion.ac.il Cited by 7632 |
The kernel recursive least-squares algorithm
We present a nonlinear version of the recursive least squares (RLS) algorithm. Our algorithm
performs linear regression in a high-dimensional feature space induced by a Mercer kernel …
performs linear regression in a high-dimensional feature space induced by a Mercer kernel …
Reinforcement learning with Gaussian processes
Gaussian Process Temporal Difference (GPTD) learning offers a Bayesian solution to the
policy evaluation problem of reinforcement learning. In this paper we extend the GPTD …
policy evaluation problem of reinforcement learning. In this paper we extend the GPTD …
[PDF][PDF] Generalization error bounds for Bayesian mixture algorithms
Bayesian approaches to learning and estimation have played a significant role in the Statistics
literature over many years. While they are often provably optimal in a frequentist setting, …
literature over many years. While they are often provably optimal in a frequentist setting, …
An introduction to boosting and leveraging
We provide an introduction to theoretical and practical aspects of Boosting and Ensemble
learning, providing a useful reference for researchers in the field of Boosting as well as for …
learning, providing a useful reference for researchers in the field of Boosting as well as for …
[PDF][PDF] Bayes meets Bellman: The Gaussian process approach to temporal difference learning
We present a novel Bayesian approach to the problem of value function estimation in
continuous state spaces. We define a probabilistic generative model for the value function by …
continuous state spaces. We define a probabilistic generative model for the value function by …
Expectation backpropagation: Parameter-free training of multilayer neural networks with continuous or discrete weights
Multilayer Neural Networks (MNNs) are commonly trained using gradient descent-based
methods, such as BackPropagation (BP). Inference in probabilistic graphical models is often …
methods, such as BackPropagation (BP). Inference in probabilistic graphical models is often …
Meta-learning by adjusting priors based on extended PAC-Bayes theory
In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning
of novel future tasks. Under the assumption that future tasks are ‘related’to previous tasks…
of novel future tasks. Under the assumption that future tasks are ‘related’to previous tasks…
Almost linear VC dimension bounds for piecewise polynomial networks
P Bartlett, V Maiorov, R Meir - Advances in neural …, 1998 - proceedings.neurips.cc
We compute upper and lower bounds on the VC dimension of feedforward networks of units
with piecewise polynomial activa (cid: 173) tion functions. We show that if the number of …
with piecewise polynomial activa (cid: 173) tion functions. We show that if the number of …
Extracting grid cell characteristics from place cell inputs using non-negative principal component analysis
10.7554/eLife.10094.001 Many recent models study the downstream projection from grid
cells to place cells, while recent data have pointed out the importance of the feedback …
cells to place cells, while recent data have pointed out the importance of the feedback …
Nonparametric time series prediction through adaptive model selection
R Meir - Machine learning, 2000 - Springer
We consider the problem of one-step ahead prediction for time series generated by an
underlying stationary stochastic process obeying the condition of absolute regularity, describing …
underlying stationary stochastic process obeying the condition of absolute regularity, describing …