相关论文: Learning to Navigate by Growing Deep Networks

Discretization invariant learning aims at learning in the infinite-dimensional function spaces with the capacity to process heterogeneous discrete representations of functions as inputs and/or outputs of a learning model. This paper…

Autonomous indoor navigation of UAVs presents numerous challenges, primarily due to the limited precision of GPS in enclosed environments. Additionally, UAVs' limited capacity to carry heavy or power-intensive sensors, such as overheight…

In the recent times, autoencoders, besides being used for compression, have been proven quite useful even for regenerating similar images or help in image denoising. They have also been explored for anomaly detection in a few cases.…

Autonomous navigation is crucial for both medical and industrial endoscopic robots, enabling safe and efficient exploration of narrow tubular environments without continuous human intervention, where avoiding contact with the inner walls…

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Layout design with complex constraints is a challenging problem to solve due to the non-uniqueness of the solution and the difficulties in incorporating the constraints into the conventional optimization-based methods. In this paper, we…

Domain adaptation solves the learning problem in a target domain by leveraging the knowledge in a relevant source domain. While remarkable advances have been made, almost all existing domain adaptation methods heavily require large amounts…

Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using deep reinforcement learning (deep RL) on various robotic…

This paper presents a technique called evolving self-supervised neural networks - neural networks that can teach themselves, intrinsically motivated, without external supervision or reward. The proposed method presents some sort-of paradigm…

Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only…

Self-supervised learning is showing great promise for monocular depth estimation, using geometry as the only source of supervision. Depth networks are indeed capable of learning representations that relate visual appearance to 3D properties…

Recent approaches for modelling dynamics of physical systems with neural networks enforce Lagrangian or Hamiltonian structure to improve prediction and generalization. However, when coordinates are embedded in high-dimensional data such as…

We propose a novel framework for enhancing robotic adaptability and learning efficiency, which integrates unsupervised trajectory segmentation with adaptive probabilistic movement primitives (ProMPs). By employing a cutting-edge deep…

A significant weakness of most current deep Convolutional Neural Networks is the need to train them using vast amounts of manu- ally labelled data. In this work we propose a unsupervised framework to learn a deep convolutional neural…

Variational autoencdoers (VAE) are a popular approach to generative modelling. However, exploiting the capabilities of VAEs in practice can be difficult. Recent work on regularised and entropic autoencoders have begun to explore the…

The manual annotation for large-scale point clouds is still tedious and unavailable for many harsh real-world tasks. Self-supervised learning, which is used on raw and unlabeled data to pre-train deep neural networks, is a promising…

The choice of an appropriate bottleneck dimension and the application of effective regularization are both essential for Autoencoders to learn meaningful representations from unlabeled data. In this paper, we introduce a new class of…

Recently, transformers have shown promising performance in learning graph representations. However, there are still some challenges when applying transformers to real-world scenarios due to the fact that deep transformers are hard to train…

Neuroevolution is one of the methodologies that can be used for learning optimal architecture during training. It uses evolutionary algorithms to generate the topology of artificial neural networks and its parameters. The main benefits are…

The autoencoder is an unsupervised learning paradigm that aims to create a compact latent representation of data by minimizing the reconstruction loss. However, it tends to overlook the fact that most data (images) are embedded in a…