Attention-based learning

Kasderidis, Stathis; Taylor, John G.

doi:10.1109/ijcnn.2004.1379964

Cited by 3 publications

(9 citation statements)

References 8 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1, formula (1) for selecting goal priorities and we define the sensory and motor attention indices as in [4,5]. The boundary attention index is defined as a sigmoid function over the value map of the energy states of the agent, and it is given by (2):…”

Section: Policy Acquisition For Multiple Goalsmentioning

confidence: 99%

“…The intrinsic weights in (1), which code the relative importance of goals are given as relative ratios: |Val G |/∑ |Val G | of the values for each goal, in our case: +20 for Transport (point B), +10 for Power Monitor (point C), -10 for MObj collision, -5 for SObj collision, +1 for Obj+ collision, -1 for Obj-collision and 5 for Collision Avoidance respectively. When approaching one of SObj, MObj, Obj+, Obj-closer than a threshold range R=3 cells, we calculate the S-AI and M-AI indices as described in [4,5]. Adding their contribution to (1) allows the alternation of priorities of goal execution and thus the determination of the currently active goal.…”

Section: Policy Acquisition For Multiple Goalsmentioning

confidence: 99%

“…In some cases collisions with moving objects took place due to false predictions regarding the future position of the objects. With further training of the predictive models for the motion of moving objects, the collisions are decreased, as it was also described in [5]. We used from 5-15 moving objects having different paths per simulation as in [5].…”

Section: Policy Acquisition For Multiple Goalsmentioning

confidence: 99%

“…With further training of the predictive models for the motion of moving objects, the collisions are decreased, as it was also described in [5]. We used from 5-15 moving objects having different paths per simulation as in [5]. The overall performance for the agent is shown in Fig.…”

Section: Policy Acquisition For Multiple Goalsmentioning

confidence: 99%

“…It has been modelled in a control theory framework by the second author [3]. Inspired by the above developments we have developed recently the Attentional Agent architecture [4] which combines a goalsbased computational model with an attention mechanism for selecting priority of goals dynamically in run time, for handling novelty and unexpected situations as well as learning of forward models based on the level of attention [5]. We now extend this model further to allow the attention mechanism to act as an alarm system when we approach limiting conditions.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Combining Attention and Value Maps

Kasderidis¹,

Taylor²

2005

Artificial Neural Networks: Biological Inspirations – ICANN 2005

View full text Add to dashboard Cite

Abstract.We present an approach where we combine attention with value maps for the purpose of acquiring a decision-making policy for multiple concurrent goals. The former component is essential for dealing with an uncertain and open environment while the latter offers a general model for building decision-making systems based on reward information. We discuss the multiple goals policy acquisition problem and justify our approach. We provide simulation results that support our solution.

show abstract

Section: Policy Acquisition For Multiple Goalsmentioning

confidence: 99%

Section: Policy Acquisition For Multiple Goalsmentioning

confidence: 99%

Section: Policy Acquisition For Multiple Goalsmentioning

confidence: 99%

Section: Policy Acquisition For Multiple Goalsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Combining Attention and Value Maps

Kasderidis¹,

Taylor²

2005

Artificial Neural Networks: Biological Inspirations – ICANN 2005

View full text Add to dashboard Cite

show abstract

Executive attention, task selection and attention-based learning in a neurally controlled simulated robot

2006

View full text Add to dashboard Cite

We describe the design and implementation of an integrated neural architecture, modelled on human executive attention, which is used to control both automatic (reactive) and willed action selection in a simulated robot. The model, based upon Norman and Shallice's supervisory attention system, incorporates important features of human attentional control: selection of an intended task over a more salient automatic task; priming of future tasks that are anticipated; and appropriate levels of persistence of focus of attention. Recognising that attention-based learning, mediated by the limbic system, and the hippocampus in particular, plays an important role in adaptive learning, we extend the Norman and Shallice model, introducing an intrinsic, attention-based learning mechanism that enhances the automaticity of willed actions and reduces future need for attentional effort. These enhanced features support a new level of attentional autonomy in the operation of the simulated robot. Some properties of the model are explored using lesion studies, leading to the identification of a correspondence between the behavioural pathologies of the simulated robot and those seen in human patients suffering dysfunction of executive attention. We discuss briefly the question of how executive attention may have arisen due to selective pressure. LaBerge identifies three characteristics traditionally associated with executive attention and considers that they should be evident in any model [36]. Grounding these three properties in the domain of action selection, we have: Keywords1. selection of a willed action over a more salient, automatically selected, action. Here, the notion of salience is intimately connected to environmentally derived stimuli in the degree to which they accord with the relevance of contending actions. However, it may also derive from internal/innate drives. For example, the salience of feeding behaviour is determined both by the availability of food in the environment and by a sense of hunger/satiation. Willed action selection involves the application of an internally derived attentional signal which results in the (more likely) performance of a less salient act in preference to a more salient act. The attentional effort needed to will one familiar action in place of another is usually intermittent, or even momentary. The willing of wholly unfamiliar actions may require more persistent attention.2. priming of an anticipated future action. Priming, too, is associated with an internally derived attentional signal. On this occasion, the potentiation does not result in the immediate expression of the behaviour, rather it enhances the salience of the behaviour so that, when the appropriate anticipated circumstances arise, there is a greater likelihood that the anticipated task will be selected. Priming is associated with enhanced speed of task switching.3. use of memory for sustained task focus. Memory is particularly important when resumption of a suspended task requires recall of some past state or stimulus...

show abstract

Attention and its Role: Theories and Models

Drigas

Karyotaki

2019

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

Motivation, affect and cognition are interrelated. However, the control of attentional deployment and more specifically, attempting to provide a more complete account of the interactions between the dorsal and ventral processing streams is still a challenge. The interaction between overt and covert attention is particularly important for models concerned with visual search. Further modeling of such interactions can assist to scrutinize many mechanisms, such as saccadic suppression, dynamic remapping of the saliency map and inhibition of return, covert pre-selection of targets for overt saccades and online understanding of complex visual scenes.

show abstract

Attention-based learning

Cited by 3 publications

References 8 publications

Combining Attention and Value Maps

Combining Attention and Value Maps

Executive attention, task selection and attention-based learning in a neurally controlled simulated robot

Attention and its Role: Theories and Models

Contact Info

Product

Resources

About