Related papers: Predictive Coding-based Deep Dynamic Neural Networ…

Humans and animals have a rich and flexible understanding of the physical world, which enables them to infer the underlying dynamical trajectories of objects and events, plausible future states, and use that to plan and anticipate the…

Visuomotor control (VMC) is an effective means of achieving basic manipulation tasks such as pushing or pick-and-place from raw images. Conditioning VMC on desired goal states is a promising way of achieving versatile skill primitives.…

Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…

Findings in recent years on the sensitivity of convolutional neural networks to additive noise, light conditions and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the…

The vast majority of visual animals actively control their eyes, heads, and/or bodies to direct their gaze toward different parts of their environment. In contrast, recent applications of reinforcement learning in robotic manipulation…

Planning for robotic manipulation requires reasoning about the changes a robot can affect on objects. When such interactions can be modelled analytically, as in domains with rigid objects, efficient planning algorithms exist. However, in…

We propose a new family of neural networks to predict the behaviors of physical systems by learning their underpinning constraints. A neural projection operator lies at the heart of our approach, composed of a lightweight network with an…

Modelling of contact-rich tasks is challenging and cannot be entirely solved using classical control approaches due to the difficulty of constructing an analytic description of the contact dynamics. Additionally, in a manipulation task like…

Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional sensing modality for…

Deep convolutional neural networks (DCNN) have enjoyed great successes in many signal processing applications because they can learn complex, non-linear causal relationships from input to output. In this light, DCNNs are well suited for the…

We explore whether useful temporal neural generative models can be learned from sequential data without back-propagation through time. We investigate the viability of a more neurocognitively-grounded approach in the context of unsupervised…

Predicting human performance in interaction tasks allows designers or developers to understand the expected performance of a target interface without actually testing it with real users. In this work, we present a deep neural net to model…

The past decade has witnessed great success of deep learning technology in many disciplines, especially in computer vision and image processing. However, deep learning-based video coding remains in its infancy. This paper reviews the…

Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories. However, it is challenging to use model-based methods in settings where the…

Visual sensation and perception refers to the process of sensing, organizing, identifying, and interpreting visual information in environmental awareness and understanding. Computational models inspired by visual perception have the…

In this work, we develop convolutional neural generative coding (Conv-NGC), a generalization of predictive coding to the case of convolution/deconvolution-based computation. Specifically, we concretely implement a flexible…

This work presents a novel method of exploring human brain-visual representations, with a view towards replicating these processes in machines. The core idea is to learn plausible computational and biological representations by correlating…

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are…

Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not…

The neural activity in the visual processing is influenced by both external stimuli and internal brain states. Ideally, a neural predictive model should account for both of them. Currently, there are no dynamic encoding models that…