Yann Lecun

Geoffrey Hinton

2021-06-21

Communications of the ACM (published)

Deep learning for AI

Geoffrey Hinton

2021-06-21

Communications of the ACM (published)

Deep learning for AI

Geoffrey Hinton

How can neural networks learn the rich internal representations required for difficult tasks such as recognizing objects or understanding la… (see more)nguage?

2021-06-21

Communications of the ACM (published)

Deep learning for AI

Geoffrey Hinton

2021-06-21

Communications of the ACM (published)

Deep learning for AI

Geoffrey Hinton

2021-06-21

Communications of the ACM (published)

Optimization of Artificial Neural Network Hyperparameters For Processing Retrospective Information

A. Rogachev

F. Scholle

I. L. Kashirin

M. Demchenko

. Justification of the selection of the architecture and hyperparameters of artificial neural networks (ANN), focused on solving various cla… (see more)sses of applied problems, is a scientific and methodological problem. Optimizing the selection of ANN hyperparameters allows you to improve the quality and speed of ANN training. Various methods of optimizing the selection of ANN hyper-parameters are known – the use of evolutionary calculations, genetic algorithms, etc., but they require the use of additional software. To optimize the process of selecting ANN hyperparameters, Google Research has developed the KerasTuner software tool. It is a platform for automated search of a set of optimal combinations of hyperparameters. In Kerastuner, you can use various methods - random search, Bayesian optimization, or Hyperband. In the numerical experiments conducted by the author, 14 hyperparameters were varied, including the number of blocks of convolutional layers and the filters forming them, the type of activation function, the parameters of the "dropout" layers, and others. The studied tools demonstrated high efficiency while simultaneously varying more than a dozen optimized parameters of the convolutional network. The calculation time on the Colaboratory platform for the various combined ANN architectures studied, including recurrent RNN networks, was several hours, even with the use of GPU graphics accelerators. For ANN, focused on the processing and recognition of retrospective information, an increase in the quality of recognition was achieved to 80 ... 95%.

Object Detection using Deep Learning

Chamarty Anusha

P. Avadhani

P. S.

Mohannad Elhamod

Martin D. Levine

Ajeet Ram Pathak

Manjusha Pandey

Siddharth S. Rautaray

Christian Szegedy

Alexander T Toshev

Dumitru Erhan

Xiaofeng Ning

Wen Zhu

Shifeng Chen

Zhong-Qiu Zhao

Peng Zheng

Shou-tao Xu

Xindong Wu

Sakshi Indolia

Anil Kumar Goswani … (see 12 more)

S. P. Mishra

Pooja Asopa

Joseph Redmon

Santosh Kumar Divvala

Ross Girshick

Ali Farhadi

M. Kruithof

Henri Bouma

Noelle M. Fischer

Klamer Schutte

Autonomous vehicles, surveillance systems, face detection systems lead to the development of accurate object detection system [1]. These sys… (see more)tems recognize, classify and localize every object in an image by drawing bounding boxes around the object [2]. These systems use existing classification models as backbone for Object Detection purpose. Object detection is the process of finding instances of real-world objects such as human faces, animals and vehicles etc., in pictures, images or in videos. An Object detection algorithm uses extracted features and learning techniques to recognize the objects in an image. In this paper, various Object Detection techniques have been studied and some of them are implemented. As a part of this paper, three algorithms for object detection in an image were implemented and their results were compared. The algorithms are “Object Detection using Deep Learning Framework by OpenCV”, “Object Detection using Tensorflow” and “Object Detection using Keras models”.

2018-12-17

International Journal of Computer Applications (published)