| 1. |
- Borga, Magnus, et al.
(författare)
-
A Binary Competition Tree for Reinforcement Learning
- 1994
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- A robust, general and computationally simple reinforcement learning system is presented. It uses a channel representation which is robust and continuous. The accumulated knowledge is represented as a reward prediction function in the outer product space of the input- and output channel vectors. Each computational unit generates an output simply by a vector-matrix multiplication and the response can therefore be calculated fast. The response and a prediction of the reward are calculated simultaneously by the same system, which makes TD-methods easy to implement if needed. Several units can cooperate to solve more complicated problems. A dynamic tree structure of linear units is grown in order to divide the knowledge space into a sufficiently number of regions in which the reward function can be properly described. The tree continuously tests split- and prune criteria in order to adapt its size to the complexity of the problem.
|
|
| 2. |
- Granlund, Gösta H., et al.
(författare)
-
Issues in Robot Vision
- 1994
-
Ingår i: Image and Vision Computing. - : Elsevier BV. - 0262-8856 .- 1872-8138. ; 12:3, s. 131-148
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper, we discuss certain issues regarding robot vision. The main theme will be the importance of the choice of information representation. We will see the implications at different parts of a robot vision structure. We deal with aspects of pre-attentive versus attentive vision, control mechanisms for low level focus of attention, and representation of motion as the orientation of hyperplanes in multdimensional time-space. Issues of scale will be touched upon, and finally, a depth-from stereo algorithm based on guadrature filter phase is presented.
|
|
| 3. |
- Karlholm, Jörgen, et al.
(författare)
-
Object Tracking Based on the Orientation Tensor Concept
- 1994
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- We apply the 3D-orientation tensor representation to construct an object tracking algorithm. 2D-line normal flow is estimated by computing the eigenvector associated with the largest eigenvalue of 3D (two spatial dimensions plus time) tensors with a planar structure. Object's true 2D velocity is computed by averaging tensors with consistent normal flows, generating a 3D line representation that corresponds to a 2D point in motion. Flow induced by camera rotation is compensated for by ignoring points with velocity consistent with the ego-rotation. A region-of-interest growing process based on motion consistency generates estimates of object size and position.
|
|
| 4. |
|
|
| 5. |
- Knutsson, Hans, et al.
(författare)
-
Robust N-Dimensional Orientation Estimation using Quadrature Filters and Tensor Whitening
- 1994
-
Ingår i: ICASSP.
-
Konferensbidrag (refereegranskat)abstract
- In this paper it is shown how estimates of local structure and orientation can be obtained using a set of spherically separable quadrature filters. The method is applicable to signals of any dimensionality the only requirement being that the filter set spans the corresponding orientation space. The estimates produced are 2:nd order tensors, the size of the tensors corresponding to the dimensionality of the input signal. A central part of the algorithm is an operation termed Tensor Whitening reminiscent of classical whitening procedures. This operation compensates exactly for any biases introduced by non-uniform filter orientation distributions and/or non-uniform filter output certainties. Examples of processing of 2D-images, 3D-volumes and 2D-image sequences are given. Sensitivity to noise and missing filter outputs are analyzed in different situations. Estimation accuracy as a function of filter orientation distributions are studied. The studies provide evidence that the algorithm is robust and preferable to other algorithms in a wide range of situations.
|
|
| 6. |
- Landelius, Tomas, et al.
(författare)
-
A Dynamic Tree Structure for Incremental Reinforcement Learning of Good Behavior
- 1994
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper addresses the idea of learning by reinforcement, within the theory of behaviorism. The reason for this choice is its generality and especially that the reinforcement learning paradigm allows systems to be designed, which can improve their behavior beyond that of their teacher. The role of the teacher is to define the reinforcement function, which acts as a description of the problem the machine is to solve. Gained knowledge is represented by a behavior probability density function which is approximated with a number of normal distributions, stored in the nodes of a binary tree. It is argued that a meaningful partitioning into local models can only be accomplished in a fused space consisting of both stimuli and responses. Given a stimulus, the system searches for responses likely to result in highly reinforced decisions by treating the sum of the two normal distributions on each level in the tree as a distribution describing the system's behavior at that resolution. The resolution of the response, as well as the tree growing and pruning processes, are controlled by a random variable based on the difference in performance between two consecutive levels in the tree. This results in a system that will never be content but will indefinitely continue to search for better solutions.
|
|
| 7. |
- Nordberg, Klas, 1963-, et al.
(författare)
-
Representation and learning of invariance
- 1994
-
Ingår i: Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference. - 0818669500 ; , s. 585-589
-
Konferensbidrag (refereegranskat)
|
|
| 8. |
- Nordberg, Klas, et al.
(författare)
-
Representation and Learning of Invariance
- 1994
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- A robust, fast and general method for estimation of object properties is proposed. It is based on a representation of theses properties in terms of channels. Each channel represents a particular value of a property, resembling the activity of biological neurons. Furthermore, each processing unit, corresponding to an artificial neuron, is a linear perceptron which operates on outer products of input data. This implies a more complex space of invariances than in the case of first order characteristic without abandoning linear theory. In general, the specific function of each processing unit has to to be learned and a fast and simple learning rule is presented. The channel representation, the processing structure and the learning rule has been tested on stereo image data showing a cube with various 3D positions and orientations. The system was able to learn a channel representation for the horizontal position, the depth, and the orientation of the cube, each property invariant to the other two.
|
|
| 9. |
|
|
| 10. |
|
|
