Deep belief net learning in a long-range vision system for autonomous off-road driving

Hadsell, Raia; Erkan, Alper Nabi; Sermanet, Pierre; Scoffier, Marco; Müller, Urs; LeCun, Yann

doi:10.1109/iros.2008.4651217

Cited by 72 publications

(41 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since 2006, deep networks have been applied with success not only in classification tasks Larochelle, Erhan, Courville, Bergstra, & Bengio, 2007;Ranzato, Boureau, & LeCun, 2008;Vincent, Larochelle, Bengio, & Manzagol, 2008;Ahmed, Yu, Xu, Gong, & Xing, 2008;Lee, Grosse, Ranganath, & Ng, 2009), but also in regression (Salakhutdinov & Hinton, 2008), dimensionality reduction (Hinton & Salakhutdinov, 2006a;Salakhutdinov & Hinton, 2007a), modeling textures (Osindero & Hinton, 2008), modeling motion (Taylor, Hinton, & Roweis, 2007;Taylor & Hinton, 2009), object segmentation (Levner, 2008), information retrieval (Salakhutdinov & Hinton, 2007b;Ranzato & Szummer, 2008;Torralba, Fergus, & Weiss, 2008), robotics (Hadsell, Erkan, Sermanet, Scoffier, Muller, & LeCun, 2008), natural language processing Weston et al, 2008;Mnih & Hinton, 2009), and collaborative filtering (Salakhutdinov, Mnih, & Hinton, 2007). Although auto-encoders, RBMs and DBNs can be trained with unlabeled data, in many of the above applications, they have been successfully used to initialize deep supervised feedforward neural networks applied to a specific task.…”

Section: How Do We Train Deep Architectures?mentioning

confidence: 99%

Learning Deep Architectures for AI

Bengio

2009

FNT in Machine Learning

6,466

3,465

View full text Add to dashboard Cite

Theoretical results suggest that in order to learn the kind of complicated functions that can represent highlevel abstractions (e.g. in vision, language, and other AI-level tasks), one may need deep architectures. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers or in complicated propositional formulae re-using many sub-formulae. Searching the parameter space of deep architectures is a difficult task, but learning algorithms such as those for Deep Belief Networks have recently been proposed to tackle this problem with notable success, beating the state-of-the-art in certain areas. This paper discusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models such as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks.

show abstract

Section: How Do We Train Deep Architectures?mentioning

confidence: 99%

Learning Deep Architectures for AI

Bengio

2009

FNT in Machine Learning

6,466

3,465

View full text Add to dashboard Cite

show abstract

“…[29,47]). In robotics, deep learning has previously been successfully used for detecting grasps on multi-channel input of RGB-D images [32] and for classifying terrain from long-range vision [18].…”

Section: Related Workmentioning

confidence: 99%

Robobarista: Object Part Based Transfer of Manipulation Trajectories from Crowd-Sourcing in 3D Pointclouds

Sung

Jin

Saxena

2017

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

There is a large variety of objects and appliances in human environments, such as stoves, coffee dispensers, juice extractors, and so on. It is challenging for a roboticist to program a robot for each of these object types and for each of their instantiations. In this work, we present a novel approach to manipulation planning based on the idea that many household objects share similarly-operated object parts. We formulate the manipulation planning as a structured prediction problem and design a deep learning model that can handle large noise in the manipulation demonstrations and learns features from three different modalities: point-clouds, language and trajectory. In order to collect a large number of manipulation demonstrations for different objects, we developed a new crowd-sourcing platform called Robobarista. We test our model on our dataset consisting of 116 objects with 249 parts along with 250 language instructions, for which there are 1225 crowd-sourced manipulation demonstrations. We further show that our robot can even manipulate objects it has never seen before.

show abstract

“…Deep learning has shown remarkable performance in various application areas [1]- [3]. An intriguing application of deep learning is within the field of autonomous driving, where neural networks are used in scene segmentation [4], object detection [5] and route planning [6]. Although neural networks are considered mature and reliable, they have the distinct disadvantage of being computationally expensive to train and use.…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network Compression for Image Classification and Object Detection

Tzelepis

Asif

Baci

et al. 2019

2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

Neural networks have been notorious for being computational expensive. This is mainly because neural networks are often over-parametrized and most likely have redundant nodes or layers as they are getting deeper and wider. Their demand for hardware resources prohibits their extensive use in embedded devices and puts restrictions on tasks like real time image classification or object detection. In this work, we propose a network agnostic model compression method infused with a novel dynamical clustering approach to reduce the computational cost and memory footprint of deep neural networks. We evaluated our new compression method on five different state-of-the-art image classification and object detection networks. In classification networks, we pruned about 95% of network parameters. In advanced detection networks such as YOLOv3, our proposed compression method managed to reduce the model parameters up to 59.70% which yielded 110× less memory without sacrificing much in accuracy.

show abstract

Deep belief net learning in a long-range vision system for autonomous off-road driving

Cited by 72 publications

References 15 publications

Learning Deep Architectures for AI

Learning Deep Architectures for AI

Robobarista: Object Part Based Transfer of Manipulation Trajectories from Crowd-Sourcing in 3D Pointclouds

Deep Neural Network Compression for Image Classification and Object Detection

Contact Info

Product

Resources

About