This document discusses feature learning for image classification. It notes that computer vision is challenging and that machine learning algorithms require good feature representations of input data rather than raw pixels. The key question is whether machine learning can automatically learn good feature representations rather than relying on hand-tuned features designed by experts. The document then outlines using unsupervised feature learning to find better representations of images than raw pixels by using machine learning algorithms on unlabeled image data.
NAO Programming using .NET and Webots 01-Introduction to NAOSetiawan Hadi
This work is part of the SAME 2013 result, in the collaboration of Computer Vision Laboratory University of Padjadjaran INDONESIA and Cognition and Interaction Laboratory Informatics Research Center University of Skövde SWEDEN.
http://blogs.unpad.ac.id/setiawanhadi/?cat=8
http://informatika.unpad.ac.id/visilab/
http://www.his.se/en/Research/informatics/Interaction-Lab/Cognition--Interaction-Lab/
“Designing Assistive Technology: A Personal Experience of Trial and Error “diannepatricia
Roberto Manduchi presentation on Cognitive Systems Institute Group weekly speaker series call on November 5, 2015. For an audio replay, find ID here: http://cognitive-science.info/community/weekly-update/
Computer Vision Fundamentals
Human vision and perception
Comparision of computer vision to human vision
Cognition
SIFT Algorithm teardown
Computer Vision Grand Challenges
NAO Programming using .NET and Webots 01-Introduction to NAOSetiawan Hadi
This work is part of the SAME 2013 result, in the collaboration of Computer Vision Laboratory University of Padjadjaran INDONESIA and Cognition and Interaction Laboratory Informatics Research Center University of Skövde SWEDEN.
http://blogs.unpad.ac.id/setiawanhadi/?cat=8
http://informatika.unpad.ac.id/visilab/
http://www.his.se/en/Research/informatics/Interaction-Lab/Cognition--Interaction-Lab/
“Designing Assistive Technology: A Personal Experience of Trial and Error “diannepatricia
Roberto Manduchi presentation on Cognitive Systems Institute Group weekly speaker series call on November 5, 2015. For an audio replay, find ID here: http://cognitive-science.info/community/weekly-update/
Computer Vision Fundamentals
Human vision and perception
Comparision of computer vision to human vision
Cognition
SIFT Algorithm teardown
Computer Vision Grand Challenges
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/auvizsystems/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Nagesh Gupta, Founder and CEO of Auviz Systems, presents the "Semantic Segmentation for Scene Understanding: Algorithms and Implementations" tutorial at the May 2016 Embedded Vision Summit.
Recent research in deep learning provides powerful tools that begin to address the daunting problem of automated scene understanding. Modifying deep learning methods, such as CNNs, to classify pixels in a scene with the help of the neighboring pixels has provided very good results in semantic segmentation. This technique provides a good starting point towards understanding a scene. A second challenge is how such algorithms can be deployed on embedded hardware at the performance required for real-world applications. A variety of approaches are being pursued for this, including GPUs, FPGAs, and dedicated hardware.
This talk provides insights into deep learning solutions for semantic segmentation, focusing on current state of the art algorithms and implementation choices. Gupta discusses the effect of porting these algorithms to fixed-point representation and the pros and cons of implementing them on FPGAs.
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/arm/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit-iodice
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Gian Marco Iodice, Software Engineer at ARM, presents the "Using SGEMM and FFTs to Accelerate Deep Learning" tutorial at the May 2016 Embedded Vision Summit.
Matrix Multiplication and the Fast Fourier Transform are numerical foundation stones for a wide range of scientific algorithms. With the emergence of deep learning, they are becoming even more important, particularly as use cases extend into mobile and embedded devices. In this presentation, lodice discusses and analyzes how these two key, computationally-intensive algorithms can be used to gain significant performance improvements for convolutional neural network (CNN) implementations.
After a brief introduction to the nature of CNN computations, Iodice explores the use of GEMM (General Matrix Multiplication) and mixed-radix FFTs to accelerate 3D convolution. He shows examples of OpenCL implementations of these functions and highlights their advantages, limitations and trade-offs. Central to the techniques explored is an emphasis on cache-efficient memory accesses and the crucial role of reduced-precision data types.
High-dynamic range (HDR) video is available to consumers today via both streaming services and optical discs. HDR video is a visually compelling experience that the average consumer can readily differentiate from existing HD content. As such, HDR video is expected to drive the next wave of consumer video. HDR TVs are available today, and HDR monitors will be available this year. The availability of these monitors will allow new user experiences on PCs, including true HDR gaming. This presentation describes what exactly HDR is and the challenges of properly displaying it on existing devices (PCs, laptops, phones, and such.) Some of the unique challenges of HDR include needing to convert content into linear light space for proper blending and scaling. This requires substantially more precision in hardware and software than we use for displaying today’s standard dynamic range content.
clCaffe*: Unleashing the Power of Intel Graphics for Deep Learning AccelerationIntel® Software
In this presentation, you will hear a story about how Intel graphics can accelerate deep learning applications. The method is simple and reproducible, with impressive results of up to four times over the original CPU performance. We introduce clCaffe*, an extension of the well-known Caffe* framework with OpenCL™ standard. This OpenCL™ standard enables primitives of the convolutional neural networks (CNN) pipeline to operate on GPU (graphics processing unit), FPGA (field programmable gate array) or any device with OpenCL support. Once set up, Caffe users can seamlessly toggle to clCaffe to take advantage of Intel graphics acceleration. Compared with original CPUs, Intel graphics presents 2.5x speedup (AlexNet classification), or 4.0x (GoogleNet classification) on 5th or 6th generation Intel® Core™ processors. Finally, we give a detailed analysis of clCaffe performance, and identify the lacking components in Intel Graphics software stack that impair its performance in the deep learning support.
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/altera/embedded-vision-training/videos/pages/may-2015-embedded-vision-summit
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Deshanand Singh, Director of Software Engineering at Altera, presents the "Efficient Implementation of Convolutional Neural Networks using OpenCL on FPGAs" tutorial at the May 2015 Embedded Vision Summit.
Convolutional neural networks (CNN) are becoming increasingly popular in embedded applications such as vision processing and automotive driver assistance systems. The structure of CNN systems is characterized by cascades of FIR filters and transcendental functions. FPGA technology offers a very efficient way of implementing these structures by allowing designers to build custom hardware datapaths that implement the CNN structure. One challenge of using FPGAs revolves around the design flow that has been traditionally centered around tedious hardware description languages.
In this talk, Deshanand gives a detailed explanation of how CNN algorithms can be expressed in OpenCL and compiled directly to FPGA hardware. He gives detail on code optimizations and provides comparisons with the efficiency of hand-coded implementations.
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/auvizsystems/embedded-vision-training/videos/pages/may-2015-embedded-vision-summit
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Nagesh Gupta, CEO and Founder of Auviz Systems, presents the "Trade-offs in Implementing Deep Neural Networks on FPGAs" tutorial at the May 2015 Embedded Vision Summit.
Video and images are a key part of Internet traffic—think of all the data generated by social networking sites such as Facebook and Instagram—and this trend continues to grow. Extracting usable information from video and images is thus a growing requirement in the data center. For example, object and face recognition are valuable for a wide range of uses, from social applications to security applications. Deep neural networks are currently the most popular form of convolutional neural networks (CNN) used in data centers for such applications. 3D convolutions are a core part of CNNs. Nagesh presents alternative implementations of 3D convolutions on FPGAs, and discusses trade-offs among them.
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/ceva/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit-siegel
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Yair Siegel, Director of Segment Marketing at CEVA, presents the "Fast Deployment of Low-power Deep Learning on CEVA Vision Processors" tutorial at the May 2016 Embedded Vision Summit.
Image recognition capabilities enabled by deep learning are benefitting more and more applications, including automotive safety, surveillance and drones. This is driving a shift towards running neural networks inside embedded devices. But, there are numerous challenges in squeezing deep learning into resource-limited devices. This presentation details a fast path for taking a neural network from research into an embedded implementation on a CEVA vision processor core, making use of CEVA’s neural network software framework. Siegel explains how the CEVA framework integrates with existing deep learning development environments like Caffe, and how it can be used to create low-power embedded systems with neural network capabilities.
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...GeeksLab Odessa
23.05.15 Одесса. Impact Hub Odessa. Конференция AI&BigData Lab
Артем Чернодуб (Computer Vision Team, ZZ Wolf)
"Распознавание изображений методом Lazy Deep Learning в фото-органайзере ZZ Photo"
В докладе рассматривается проблема распознавания изображений методами машинного зрения. Проводится краткий обзор существующих подзадач в этой области (детекция обьектов, классификация сцен, ассоциативный поиск в базах изображений, распознавание лиц и др.) и современных методов их решения с акцентом на глубокое обучение (Deep Learning).
Подробнее:
http://geekslab.co/
https://www.facebook.com/GeeksLab.co
https://www.youtube.com/user/GeeksLabVideo
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/altera/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Bill Jenkins, Senior Product Specialist for High Level Design Tools at Intel, presents the "Accelerating Deep Learning Using Altera FPGAs" tutorial at the May 2016 Embedded Vision Summit.
While large strides have recently been made in the development of high-performance systems for neural networks based on multi-core technology, significant challenges in power, cost and, performance scaling remain. Field-programmable gate arrays (FPGAs) are a natural choice for implementing neural networks because they can combine computing, logic, and memory resources in a single device. Intel's Programmable Solutions Group has developed a scalable convolutional neural network reference design for deep learning systems using the OpenCL programming language built with our SDK for OpenCL. The design performance is being benchmarked using several popular CNN benchmarks: CIFAR-10, ImageNet and KITTI.
Building the CNN with OpenCL kernels allows true scaling of the design from smaller to larger devices and from one device generation to the next. New designs can be sized using different numbers of kernels at each layer. Performance scaling from one generation to the next also benefits from architectural advancements, such as floating-point engines and frequency scaling. Thus, you achieve greater than linear performance and performance per watt scaling with each new series of devices.
A comprehensive tutorial on Convolutional Neural Networks (CNN) which talks about the motivation behind CNNs and Deep Learning in general, followed by a description of the various components involved in a typical CNN layer. It explains the theory involved with the different variants used in practice and also, gives a big picture of the whole network by putting everything together.
Next, there's a discussion of the various state-of-the-art frameworks being used to implement CNNs to tackle real-world classification and regression problems.
Finally, the implementation of the CNNs is demonstrated by implementing the paper 'Age ang Gender Classification Using Convolutional Neural Networks' by Hassner (2015).
Chen Sagiv, co founder and co CEO of SagivTech, gave an introduction talk to Computer Vision at She Codes branch in Google Campus TLV.
In the talk an overview was given on what is computer vision, where it is used, some basic notions and algorithms and the AI revolution.
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/auvizsystems/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Nagesh Gupta, Founder and CEO of Auviz Systems, presents the "Semantic Segmentation for Scene Understanding: Algorithms and Implementations" tutorial at the May 2016 Embedded Vision Summit.
Recent research in deep learning provides powerful tools that begin to address the daunting problem of automated scene understanding. Modifying deep learning methods, such as CNNs, to classify pixels in a scene with the help of the neighboring pixels has provided very good results in semantic segmentation. This technique provides a good starting point towards understanding a scene. A second challenge is how such algorithms can be deployed on embedded hardware at the performance required for real-world applications. A variety of approaches are being pursued for this, including GPUs, FPGAs, and dedicated hardware.
This talk provides insights into deep learning solutions for semantic segmentation, focusing on current state of the art algorithms and implementation choices. Gupta discusses the effect of porting these algorithms to fixed-point representation and the pros and cons of implementing them on FPGAs.
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/arm/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit-iodice
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Gian Marco Iodice, Software Engineer at ARM, presents the "Using SGEMM and FFTs to Accelerate Deep Learning" tutorial at the May 2016 Embedded Vision Summit.
Matrix Multiplication and the Fast Fourier Transform are numerical foundation stones for a wide range of scientific algorithms. With the emergence of deep learning, they are becoming even more important, particularly as use cases extend into mobile and embedded devices. In this presentation, lodice discusses and analyzes how these two key, computationally-intensive algorithms can be used to gain significant performance improvements for convolutional neural network (CNN) implementations.
After a brief introduction to the nature of CNN computations, Iodice explores the use of GEMM (General Matrix Multiplication) and mixed-radix FFTs to accelerate 3D convolution. He shows examples of OpenCL implementations of these functions and highlights their advantages, limitations and trade-offs. Central to the techniques explored is an emphasis on cache-efficient memory accesses and the crucial role of reduced-precision data types.
High-dynamic range (HDR) video is available to consumers today via both streaming services and optical discs. HDR video is a visually compelling experience that the average consumer can readily differentiate from existing HD content. As such, HDR video is expected to drive the next wave of consumer video. HDR TVs are available today, and HDR monitors will be available this year. The availability of these monitors will allow new user experiences on PCs, including true HDR gaming. This presentation describes what exactly HDR is and the challenges of properly displaying it on existing devices (PCs, laptops, phones, and such.) Some of the unique challenges of HDR include needing to convert content into linear light space for proper blending and scaling. This requires substantially more precision in hardware and software than we use for displaying today’s standard dynamic range content.
clCaffe*: Unleashing the Power of Intel Graphics for Deep Learning AccelerationIntel® Software
In this presentation, you will hear a story about how Intel graphics can accelerate deep learning applications. The method is simple and reproducible, with impressive results of up to four times over the original CPU performance. We introduce clCaffe*, an extension of the well-known Caffe* framework with OpenCL™ standard. This OpenCL™ standard enables primitives of the convolutional neural networks (CNN) pipeline to operate on GPU (graphics processing unit), FPGA (field programmable gate array) or any device with OpenCL support. Once set up, Caffe users can seamlessly toggle to clCaffe to take advantage of Intel graphics acceleration. Compared with original CPUs, Intel graphics presents 2.5x speedup (AlexNet classification), or 4.0x (GoogleNet classification) on 5th or 6th generation Intel® Core™ processors. Finally, we give a detailed analysis of clCaffe performance, and identify the lacking components in Intel Graphics software stack that impair its performance in the deep learning support.
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/altera/embedded-vision-training/videos/pages/may-2015-embedded-vision-summit
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Deshanand Singh, Director of Software Engineering at Altera, presents the "Efficient Implementation of Convolutional Neural Networks using OpenCL on FPGAs" tutorial at the May 2015 Embedded Vision Summit.
Convolutional neural networks (CNN) are becoming increasingly popular in embedded applications such as vision processing and automotive driver assistance systems. The structure of CNN systems is characterized by cascades of FIR filters and transcendental functions. FPGA technology offers a very efficient way of implementing these structures by allowing designers to build custom hardware datapaths that implement the CNN structure. One challenge of using FPGAs revolves around the design flow that has been traditionally centered around tedious hardware description languages.
In this talk, Deshanand gives a detailed explanation of how CNN algorithms can be expressed in OpenCL and compiled directly to FPGA hardware. He gives detail on code optimizations and provides comparisons with the efficiency of hand-coded implementations.
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/auvizsystems/embedded-vision-training/videos/pages/may-2015-embedded-vision-summit
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Nagesh Gupta, CEO and Founder of Auviz Systems, presents the "Trade-offs in Implementing Deep Neural Networks on FPGAs" tutorial at the May 2015 Embedded Vision Summit.
Video and images are a key part of Internet traffic—think of all the data generated by social networking sites such as Facebook and Instagram—and this trend continues to grow. Extracting usable information from video and images is thus a growing requirement in the data center. For example, object and face recognition are valuable for a wide range of uses, from social applications to security applications. Deep neural networks are currently the most popular form of convolutional neural networks (CNN) used in data centers for such applications. 3D convolutions are a core part of CNNs. Nagesh presents alternative implementations of 3D convolutions on FPGAs, and discusses trade-offs among them.
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/ceva/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit-siegel
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Yair Siegel, Director of Segment Marketing at CEVA, presents the "Fast Deployment of Low-power Deep Learning on CEVA Vision Processors" tutorial at the May 2016 Embedded Vision Summit.
Image recognition capabilities enabled by deep learning are benefitting more and more applications, including automotive safety, surveillance and drones. This is driving a shift towards running neural networks inside embedded devices. But, there are numerous challenges in squeezing deep learning into resource-limited devices. This presentation details a fast path for taking a neural network from research into an embedded implementation on a CEVA vision processor core, making use of CEVA’s neural network software framework. Siegel explains how the CEVA framework integrates with existing deep learning development environments like Caffe, and how it can be used to create low-power embedded systems with neural network capabilities.
AI&BigData Lab. Артем Чернодуб "Распознавание изображений методом Lazy Deep ...GeeksLab Odessa
23.05.15 Одесса. Impact Hub Odessa. Конференция AI&BigData Lab
Артем Чернодуб (Computer Vision Team, ZZ Wolf)
"Распознавание изображений методом Lazy Deep Learning в фото-органайзере ZZ Photo"
В докладе рассматривается проблема распознавания изображений методами машинного зрения. Проводится краткий обзор существующих подзадач в этой области (детекция обьектов, классификация сцен, ассоциативный поиск в базах изображений, распознавание лиц и др.) и современных методов их решения с акцентом на глубокое обучение (Deep Learning).
Подробнее:
http://geekslab.co/
https://www.facebook.com/GeeksLab.co
https://www.youtube.com/user/GeeksLabVideo
For the full video of this presentation, please visit:
http://www.embedded-vision.com/platinum-members/altera/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit
For more information about embedded vision, please visit:
http://www.embedded-vision.com
Bill Jenkins, Senior Product Specialist for High Level Design Tools at Intel, presents the "Accelerating Deep Learning Using Altera FPGAs" tutorial at the May 2016 Embedded Vision Summit.
While large strides have recently been made in the development of high-performance systems for neural networks based on multi-core technology, significant challenges in power, cost and, performance scaling remain. Field-programmable gate arrays (FPGAs) are a natural choice for implementing neural networks because they can combine computing, logic, and memory resources in a single device. Intel's Programmable Solutions Group has developed a scalable convolutional neural network reference design for deep learning systems using the OpenCL programming language built with our SDK for OpenCL. The design performance is being benchmarked using several popular CNN benchmarks: CIFAR-10, ImageNet and KITTI.
Building the CNN with OpenCL kernels allows true scaling of the design from smaller to larger devices and from one device generation to the next. New designs can be sized using different numbers of kernels at each layer. Performance scaling from one generation to the next also benefits from architectural advancements, such as floating-point engines and frequency scaling. Thus, you achieve greater than linear performance and performance per watt scaling with each new series of devices.
A comprehensive tutorial on Convolutional Neural Networks (CNN) which talks about the motivation behind CNNs and Deep Learning in general, followed by a description of the various components involved in a typical CNN layer. It explains the theory involved with the different variants used in practice and also, gives a big picture of the whole network by putting everything together.
Next, there's a discussion of the various state-of-the-art frameworks being used to implement CNNs to tackle real-world classification and regression problems.
Finally, the implementation of the CNNs is demonstrated by implementing the paper 'Age ang Gender Classification Using Convolutional Neural Networks' by Hassner (2015).
Chen Sagiv, co founder and co CEO of SagivTech, gave an introduction talk to Computer Vision at She Codes branch in Google Campus TLV.
In the talk an overview was given on what is computer vision, where it is used, some basic notions and algorithms and the AI revolution.
El comportamiento de nuestro robot, Golem-II+, es regulado por una Arquitectura Orientada a la Interacción Cognitiva (IOCA, por sus siglas en inglés). Un diagrama de IOCA se puede ver a continuación
An Approach for Object and Scene Detection for Blind Peoples Using Vocal Vision.IJERA Editor
This system help the blind peoples for the navigation without the help of third person so blind person can perform its work independently. This system implemented on android device in which object detection and scene detection implemented, so after detection there will be text to speech conversion so user or blind person can get message from that android device with the help of headphone connected to that device. Our project will help blind people to understand the images which will be converted to sound with the help of webcam. We shall capture images in front of blind peoples .The captured image will be processed through our algorithms which will enhances the image data. The hardware component will have its own database. The processed image is compare with the database in the hardware component .The result after processing and comparing will be converted into speech signals. The headphones guide the blind peoples.
The Indian economy is classified into different sectors to simplify the analysis and understanding of economic activities. For Class 10, it's essential to grasp the sectors of the Indian economy, understand their characteristics, and recognize their importance. This guide will provide detailed notes on the Sectors of the Indian Economy Class 10, using specific long-tail keywords to enhance comprehension.
For more information, visit-www.vavaclasses.com
We all have good and bad thoughts from time to time and situation to situation. We are bombarded daily with spiraling thoughts(both negative and positive) creating all-consuming feel , making us difficult to manage with associated suffering. Good thoughts are like our Mob Signal (Positive thought) amidst noise(negative thought) in the atmosphere. Negative thoughts like noise outweigh positive thoughts. These thoughts often create unwanted confusion, trouble, stress and frustration in our mind as well as chaos in our physical world. Negative thoughts are also known as “distorted thinking”.
Synthetic Fiber Construction in lab .pptxPavel ( NSTU)
Synthetic fiber production is a fascinating and complex field that blends chemistry, engineering, and environmental science. By understanding these aspects, students can gain a comprehensive view of synthetic fiber production, its impact on society and the environment, and the potential for future innovations. Synthetic fibers play a crucial role in modern society, impacting various aspects of daily life, industry, and the environment. ynthetic fibers are integral to modern life, offering a range of benefits from cost-effectiveness and versatility to innovative applications and performance characteristics. While they pose environmental challenges, ongoing research and development aim to create more sustainable and eco-friendly alternatives. Understanding the importance of synthetic fibers helps in appreciating their role in the economy, industry, and daily life, while also emphasizing the need for sustainable practices and innovation.
The French Revolution, which began in 1789, was a period of radical social and political upheaval in France. It marked the decline of absolute monarchies, the rise of secular and democratic republics, and the eventual rise of Napoleon Bonaparte. This revolutionary period is crucial in understanding the transition from feudalism to modernity in Europe.
For more information, visit-www.vavaclasses.com
Palestine last event orientationfvgnh .pptxRaedMohamed3
An EFL lesson about the current events in Palestine. It is intended to be for intermediate students who wish to increase their listening skills through a short lesson in power point.
Unit 8 - Information and Communication Technology (Paper I).pdfThiyagu K
This slides describes the basic concepts of ICT, basics of Email, Emerging Technology and Digital Initiatives in Education. This presentations aligns with the UGC Paper I syllabus.
Operation “Blue Star” is the only event in the history of Independent India where the state went into war with its own people. Even after about 40 years it is not clear if it was culmination of states anger over people of the region, a political game of power or start of dictatorial chapter in the democratic setup.
The people of Punjab felt alienated from main stream due to denial of their just demands during a long democratic struggle since independence. As it happen all over the word, it led to militant struggle with great loss of lives of military, police and civilian personnel. Killing of Indira Gandhi and massacre of innocent Sikhs in Delhi and other India cities was also associated with this movement.
3. Machine learning and feature representations Input Input space Learning algorithm pixel 1 Motorbikes “ Non”-Motorbikes pixel 1 pixel 2
4. Machine learning and feature representations Input Input space Feature space Feature representation Learning algorithm pixel 1 “ wheel” Motorbikes “ Non”-Motorbikes handle wheel
5. How is computer perception done? Object detection Audio classification Helicopter control Image Low-level vision features Recognition Image Grasp point Low-level features Low-level state features Action Helicopter Audio Low-level audio features Speaker identification
8. Audio features ZCR Spectrogram MFCC Rolloff Flux Problems of hand-tuned features 1. Needs expert knowledge 2. Time-consuming and expensive 3. Does not generalize to other domains
9. Computer vision is more than pictures Can we automatically learn good feature representations? Key question: Can we automatically learn a good feature representation? Camera array 3d range scan (laser scanner) 3d range scans (flash lidar) Audio Images Visible light image Thermal Infrared Thermal Infrared Video
11. Sensor representation in the brain [BrainPort; Martinez et al; Roe et al.] Human echolocation (sonar) Auditory cortex learns to see. Auditory Cortex Seeing with your tongue
12.
13. The goal of Unsupervised Feature Learning Unlabeled images Learning algorithm Feature representation
14.
Editor's Notes
Good faith effort to implement state-of-the-art. Cluttered scenes.
Where do we get these low-level representations from?
XXX AI dedicated substantial amount of effort to high-level feature representations. XXX Should now dedicate equal amount to low-level feature representations, because they’re what’s really needed to get our systems to work.
Where do we get these low-level representations from?
Goal of workshop: Give you high level overview of some of the ideas in ufl. Also, give you ability to go home and start implementing something. (At end, will have resources.)