Learning in compressed space

Fabisch, Alexander; Kassahun, Yohannes; Wöhrle, Hendrik; Kirchner, Frank

doi:10.1016/j.neunet.2013.01.020

Cited by 12 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [164], a nonconvex integrated transformed L 1 regularizer applied to the weight matrix space is introduced to remove redundant connections and unnecessary neurons simultaneously. It is shown in [165] that compressing the weights of a layer has the same effect as compressing the input of the layer.…”

Section: Regularization-based Methodsmentioning

confidence: 99%

Perceptron: Learning, Generalization, Model Selection, Fault Tolerance, and Role in the Deep Learning Era

Leung

Mow

et al. 2022

Mathematics

View full text Add to dashboard Cite

The single-layer perceptron, introduced by Rosenblatt in 1958, is one of the earliest and simplest neural network models. However, it is incapable of classifying linearly inseparable patterns. A new era of neural network research started in 1986, when the backpropagation (BP) algorithm was rediscovered for training the multilayer perceptron (MLP) model. An MLP with a large number of hidden nodes can function as a universal approximator. To date, the MLP model is the most fundamental and important neural network model. It is also the most investigated neural network model. Even in this AI or deep learning era, the MLP is still among the few most investigated and used neural network models. Numerous new results have been obtained in the past three decades. This survey paper gives a comprehensive and state-of-the-art introduction to the perceptron model, with emphasis on learning, generalization, model selection and fault tolerance. The role of the perceptron model in the deep learning era is also described. This paper provides a concluding survey of perceptron learning, and it covers all the major achievements in the past seven decades. It also serves a tutorial for perceptron learning.

show abstract

Section: Regularization-based Methodsmentioning

confidence: 99%

Perceptron: Learning, Generalization, Model Selection, Fault Tolerance, and Role in the Deep Learning Era

Leung

Mow

et al. 2022

Mathematics

View full text Add to dashboard Cite

show abstract

“…Reliable and successful solutions come from the fields of RL, [14][15][16][17][18][19][20][21][22][23] optimal control, 24 and black-box optimization. [25][26][27][28][29][30] These approaches often rely on special types of policies for robotic problems, for example, dynamical movement primitives. [31][32][33][34][35] For details on RL in robotics please refer to Kober et al 36 BOLERO provides implementations for several of these algorithms.…”

Section: Background and Related Workmentioning

confidence: 99%

BOLeRo: Behavior optimization and learning for robots

Fabisch

Langosz

Kirchner

2020

International Journal of Advanced Robotic Systems

Self Cite

View full text Add to dashboard Cite

Reinforcement learning and behavior optimization are becoming more and more popular in the field of robotics because algorithms are mature enough to tackle real problems in this domain. Robust implementations of state-of-the-art algorithms are often not publicly available though, and experiments are hardly reproducible because open-source implementations are often not available or are still in a stage of research code. Consequently, often it is infeasible to deploy these algorithms on robotic systems. BOLeRo closes this gap for policy search and evolutionary algorithms by delivering open-source implementations of behavior learning algorithms for robots. It is easy to integrate in robotic middlewares and it can be used to compare methods and develop prototypes in simulation.

show abstract

“…1. Previous work of (Koutnik et al, 2010;Fabisch et al, 2013) has already demonstrated that a compression of the parameter space by use of multi layer perceptrons (MLPs) leads to an acceleration of optimization for reinforcement tasks. Reduction of the search spaces by manifolds for value function approximation and abstraction of the whole state-space into sub areas for terrain navigation can be beneficial in case of reinforcement learning.…”

Section: Optimization In Hybrid Spacesmentioning

confidence: 99%

Bootstrapping of Parameterized Skills Through Hybrid Optimization in Task and Policy Spaces

Queißer

Steil

2018

Front. Robot. AI

View full text Add to dashboard Cite

Modern robotic applications create high demands on adaptation of actions with respect to variance in a given task. Reinforcement learning is able to optimize for these changing conditions, but relearning from scratch is hardly feasible due to the high number of required rollouts. We propose a parameterized skill that generalizes to new actions for changing task parameters, which is encoded as a meta-learner that provides parameters for task-specific dynamic motion primitives. Our work shows that utilizing parameterized skills for initialization of the optimization process leads to a more effective incremental task learning. In addition, we introduce a hybrid optimization method that combines a fast coarse optimization on a manifold of policy parameters with a fine grained parameter search in the unrestricted space of actions. The proposed algorithm reduces the number of required rollouts for adaptation to new task conditions. Application in illustrative toy scenarios, for a 10-DOF planar arm, and a humanoid robot point reaching task validate the approach.

show abstract

Learning in compressed space

Cited by 12 publications

References 17 publications

Perceptron: Learning, Generalization, Model Selection, Fault Tolerance, and Role in the Deep Learning Era

Perceptron: Learning, Generalization, Model Selection, Fault Tolerance, and Role in the Deep Learning Era

BOLeRo: Behavior optimization and learning for robots

Bootstrapping of Parameterized Skills Through Hybrid Optimization in Task and Policy Spaces

Contact Info

Product

Resources

About