Multi-column deep neural network for traffic sign classification

Cireşan, Dan; Meier, Ueli; Masci, Jonathan; Schmidhuber, Juergen

doi:10.1016/j.neunet.2012.02.023

Cited by 895 publications

(443 citation statements)

References 21 publications

Supporting

Mentioning

427

Contrasting

Unclassified

Order By: Relevance

“…An ensemble of GPU-MPCNNs was the first system to achieve superhuman visual pattern recognition (Ciresan et al, 2011b(Ciresan et al, , 2012b) in a controlled competition, namely, the IJCNN 2011 traffic sign recognition contest in San Jose (CA) (Stallkamp et al, 2011(Stallkamp et al, , 2012. This is of interest for fully autonomous, self-driving cars in traffic (e.g., Dickmanns et al, 1994).…”

Section: : Mpcnns On Gpu Achieve Superhuman Vision Performancementioning

confidence: 99%

Deep learning in neural networks: An overview

2015

Self Cite

View full text Add to dashboard Cite

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.LATEX source: http://www.idsia.ch/˜juergen/DeepLearning8Oct2014.tex Complete BIBTEX file (888 kB): http://www.idsia.ch/˜juergen/deep.bib Preface This is the preprint of an invited Deep Learning (DL) overview. One of its goals is to assign credit to those who contributed to the present state of the art. I acknowledge the limitations of attempting to achieve this goal. The DL research community itself may be viewed as a continually evolving, deep network of scientists who have influenced each other in complex ways. Starting from recent DL results, I tried to trace back the origins of relevant ideas through the past half century and beyond, sometimes using "local search" to follow citations of citations backwards in time. Since not all DL publications properly acknowledge earlier relevant work, additional global search strategies were employed, aided by consulting numerous neural network experts. As a result, the present preprint mostly consists of references. Nevertheless, through an expert selection bias I may have missed important work. A related bias was surely introduced by my special familiarity with the work of my own DL research group in the past quarter-century. For these reasons, this work should be viewed as merely a snapshot of an ongoing credit assignment process. To help improve it, please do not hesitate to send corrections and suggestions to juergen@idsia.ch.

show abstract

Section: : Mpcnns On Gpu Achieve Superhuman Vision Performancementioning

confidence: 99%

Deep learning in neural networks: An overview

2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, our CTC-trained [22] Training an RNN by standard methods is similar to training a feedforward NN (FNN) with many layers, which runs into similar problems [28]. However, our recent deep FNN with special internal architecture overcome these problems to the extent that they are currently winning many international pattern recognition contests [6,[8][9][10][11]78] (see list of won competitions below). None of this requires the traditional sophisticated computer vision techniques developed over the past six decades or so.…”

Section: Recurrent / Deep Neural Networkmentioning

confidence: 99%

“…Onset of the unprecedented population explosion driving many other developments. European colonialism at its short-lived peak 10. Ω − 1 lifetime: Post-World War II society and pop culture emerges.…”

Section: Is History Converging? Again?mentioning

confidence: 99%

New Millennium AI and the Convergence of History: Update of 2012

Schmidhuber

2012

The Frontiers Collection

Self Cite

View full text Add to dashboard Cite

Summary. Artificial Intelligence (AI) has recently become a real formal science: the new millennium brought the first mathematically sound, asymptotically optimal, universal problem solvers, providing a new, rigorous foundation for the previously largely heuristic field of General AI and embedded agents. There also has been rapid progress in not quite universal but still rather general and practical artificial recurrent neural networks for learning sequenceprocessing programs, now yielding state-of-the-art results in real world applications. And the computing power per Euro is still growing by a factor of 100-1000 per decade, greatly increasing the feasibility of neural networks in general, which have started to yield humancompetitive results in challenging pattern recognition competitions. Finally, a recent formal theory of fun and creativity identifies basic principles of curious and creative machines, laying foundations for artificial scientists and artists. Here I will briefly review some of the new results of my lab at IDSIA, and speculate about future developments, pointing out that the time intervals between the most notable events in over 40,000 years or 2 9 lifetimes of human history have sped up exponentially, apparently converging to zero within the next few decades. Or is this impression just a by-product of the way humans allocate memory space to past events? Note: this is the 2012 update of a 2007 publication [73]. Compare also the 2006 celebration of 75 years of AI [71].

show abstract

“…In general, pattern recognition schemes can directly handle the samples which are represented in a vector space. In most neural networks system, such as character recognition [20] and traffic signs recognition [21], the samples can be easily converted into feature vectors after normalizing the size of the input images.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Triaxial Accelerometer-Based Energy Efficient Human Activity Recognition Using Smartphone

2017

IJAERD

View full text Add to dashboard Cite

show abstract

Multi-column deep neural network for traffic sign classification

Cited by 895 publications

References 21 publications

Deep learning in neural networks: An overview

Deep learning in neural networks: An overview

New Millennium AI and the Convergence of History: Update of 2012

Real-Time Triaxial Accelerometer-Based Energy Efficient Human Activity Recognition Using Smartphone

Contact Info

Product

Resources

About