Potentials and Limitations of Deep Neural Networks for Cognitive Robots
Explore this paper's citation graph
Summary
It is argued that those architectures are potentially interesting for cognitive robots regarding their perceptual representation power for audio and vision data and the rather unexplored area of Reservoir Computing qualifies to be an integral part of sequential learning in this context.
- Type
- preprint
- Published
- 2018-05-02
- Cited by
- 5
- References
- 28
- Access
- Open access
- OpenAlex
- https://openalex.org/W2799148389
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:13754046
Keywords
Cognition, Artificial neural network, Deep neural networks, Robot, Computer science
References
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
- Learning of embodied interaction dynamics with recurrent neural networks: some exploratory experiments
- Information dynamics based self-adaptive reservoir for delay temporal memory tasks
- What is Intrinsic Motivation? A Typology of Computational Approaches
- Large-Scale Video Classification with Convolutional Neural Networks
- Grounding Action Words in the Sensorimotor Interaction with the World: Experiments with a Simulated iCub Humanoid Robot
- Exploring the acquisition and production of grammatical constructions through human-robot interaction with echo state networks
- On Learning Navigation Behaviors for Small Mobile Robots With Reservoir Computing Architectures
- A self-organising network that grows when required
- Infant grasp learning: a computational model
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
- Parental scaffolding as a bootstrapping mechanism for learning grasp affordances and imitation skills
- Design of a Central Pattern Generator Using Reservoir Computing for Learning Human Motion
- Investigating Echo-State Networks Dynamics by Means of Recurrence Analysis
- Towards Deep Developmental Learning
- Learning to Perceive the World as Probabilistic or Deterministic via Interaction With Others: A Neuro-Robotics Experiment
- Advantages and limitations of reservoir computing on model learning for robot control
- Reservoir Computing: Quo Vadis?
- Emotion-modulated attention improves expression recognition: A deep learning model
Cited by
- Solving visual object ambiguities when pointing: an unsupervised learning approach
- Development of hardware-software complex for adaptive sorting of solid domestic waste
- Exploring the Efficiencies of Spectral Isolation for Intelligent Wear Monitoring of Micro Drill Bit Automatic Regrinding In-Line Systems
- Spatio-Temporal Data Interpretation Based on Perceptional Model
- Development of hardware-software complex for adaptive sorting of solid domestic waste
Related papers
- Hierarchical Organization of Robots: A Social Simulation Study
- Cooperative Fishing Boat Robots Model for Extreme Worker
- Flexible Robots - A Survey
- Artificial Neural Network (ANN) Method for Predicting of Hydrochemical Types of Salt Lakes
- Cognition and life: the autonomy of cognition.
- Two views on the cognitive brain
- Computational approaches to cognition: top-down approaches.
- Toward studying cognition in a dish
- Is Cognition Enough to Explain Cognitive Development?