- talks - lists.cs.princeton.edu

Deep learning With ZNN- ROOM CHANGE-now in A02, Princeton Neuroscience Institute
by Michele J. Brown 20 Oct '14

20 Oct '14

The event has been moved to a larger room, PNI A02. We apologize that food will not be available until the beginning of the hands-on session at 1:30pm, as food is not allowed in A02. -------- Deep learning with ZNN Aleksandar Zlateski and Kisuk Lee October 20, 2014 12pm seminar 1:30pm hands-on session Princeton Neuroscience Institute A02 Aleks will describe ZNN, his multicore CPU implementation of deep learning for 2D and 3D convolutional networks. He will present preliminary benchmarks showing that ZNN is competitive with GPU-accelerated deep learning (currently the dominant approach). The use of CPUs avoids the limited RAM of GPUs, and reduces software development cost. Kisuk will present a how-to tutorial on using ZNN, illustrated with the application of boundary detection in 3D nanoscale brain images. The talks will be followed by a hands-on session including installation of ZNN and application to an image segmentation challenge (http://brainiac2.mit.edu/isbi_challenge/).[1] Participants should bring their own laptops, and will require access to their own Linux machine. Participants are encouraged to install ZNN (https://github.com/seung-lab/znn-release)[2] prior to the event, as well as the boost and fftw libraries.

1 0

Colloquium Speaker Yann LeCun Weds Oct 22, 4:30pm
by Nicole E. Wagenblast 20 Oct '14

20 Oct '14

Yann LeCun, Facebook AI Research and Center for Data Science, New York University The Unreasonable Effectiveness of Deep Learning Wednesday, October 22 , 4:30pm Computer Science 105 The emergence of large datasets, parallel computers, and new machine learning methods, have enabled the deployment of highly-accurate computer perception systems and are opening the door to a wide deployment of AI systems. A key component in AI systems is a module, sometimes called a feature extractor, that turns raw inputs into suitable internal representations. But designing and building such a module requires a considerable amount of engineering efforts and domain expertise. Deep Learning methods have provided a way to automatically learn good representations of data from labeled or unlabeled samples. Deep architectures are composed of successive stages in which data representations are increasingly global, abstract, and invariant to irrelevant transformations of the input. Deep learning enables end-to-end training of these architectures, from raw inputs to ultimate outputs. The convolutional network model (ConvNet) is a particular type of deep architecture somewhat inspired by biology, which consists of multiple stages of filter banks, interspersed with non-linear operators, and spatial pooling. ConvNets have become the record holder for a wide variety of benchmarks, including object detection, localization and recognition in image, semantic segmentation and labeling, face recognition, acoustic modeling for speech recognition, drug design, handwriting recognition, biological image segmentation, etc. The most recent systems deployed by Facebook, Google, NEC, IBM, Microsoft, Baidu, Yahoo and others for image understanding, speech recognition, and natural language processing use deep learning. Many of these systems use very large and very deep ConvNets with billions of connections, trained in supervised mode. But many new applications require the use of unsupervised feature learning. A number of such methods based on sparse auto-encoder will be presented. Several applications will be shown through videos and live demos, including a category-level object recognition system that can be trained on the fly, a scene parsing system that can label every pixel in an image with the category of the object it belongs to (scene parsing), an object localization and detection system, and several natural language processing systems. Specialized hardware architectures that run these systems in real time will also be described. Yann LeCun is Director of AI Research at Facebook, and Silver Professor of Data Science, Computer Science, Neural Science, and Electrical Engineering at New York University, affiliated with the NYU Center for Data Science, the Courant Institute of Mathematical Science, the Center for Neural Science, and the Electrical and Computer Engineering Department. He received the Electrical Engineer Diploma from Ecole Supérieure d'Ingénieurs en Electrotechnique et Electronique (ESIEE), Paris in 1983, and a PhD in Computer Science from Université Pierre et Marie Curie (Paris) in 1987. After a postdoc at the University of Toronto, he joined AT&T Bell Laboratories in Holmdel, NJ in 1988. He became head of the Image Processing Research Department at AT&T Labs-Research in 1996, and joined NYU as a professor in 2003, after a brief period as a Fellow of the NEC Research Institute in Princeton. From 2012 to 2014 he directed NYU's initiative in data science and became the founding director of the NYU Center for Data Science. He was named Director of AI Research at Facebook in late 2013 and retains a part-time position on the NYU faculty. His current interests include AI, machine learning, computer perception, mobile robotics, and computational neuroscience. He has published over 180 technical papers and book chapters on these topics as well as on neural networks, handwriting recognition, image processing and compression, and on dedicated circuits and architectures for computer perception. The character recognition technology he developed at Bell Labs is used by several banks around the world to read checks and was reading between 10 and 20% of all the checks in the US in the early 2000s. His image compression technology, called DjVu, is used by hundreds of web sites and publishers and millions of users to access scanned documents on the Web. Since the mid 1980's he has been working on deep learning methods, particularly the convolutional network model, which is the basis of many products and services deployed by companies such as Facebook, Google, Microsoft, Baidu, IBM, NEC, AT&T and others for image and video understanding, document recognition, human-computer interaction, and speech recognition. LeCun has been on the editorial board of IJCV, IEEE PAMI, and IEEE Trans. Neural Networks, was program chair of CVPR'06, and is chair of ICLR 2013 and 2014. He is on the science advisory board of Institute for Pure and Applied Mathematics, and Neural Computation and Adaptive Perception Program of the Canadian Institute for Advanced Research. He has advised many large and small companies about machine learning technology, including several startups he co-founded. He is the lead faculty at NYU for the Moore-Sloan Data Science Environment, a $36M initiative in collaboration with UC Berkeley and University of Washington to develop data-driven methods in the sciences. He is the recipient of the 2014 IEEE Neural Network Pioneer Award.

1 0

Deep learning with ZNN-12pm seminar-- Neuroscience Institute 159 TODAY
by Michele J. Brown 20 Oct '14

20 Oct '14

Deep learning with ZNN Aleksandar Zlateski and Kisuk Lee October 20, 2014 12pm seminar 1:30pm hands-on session Princeton Neuroscience Institute 159 Aleks will describe ZNN, his multicore CPU implementation of deep learning for 2D and 3D convolutional networks. He will present preliminary benchmarks showing that ZNN is competitive with GPU-accelerated deep learning (currently the dominant approach). The use of CPUs avoids the limited RAM of GPUs, and reduces software development cost. Kisuk will present a how-to tutorial on using ZNN, illustrated with the application of boundary detection in 3D nanoscale brain images. The talks will be followed by a hands-on session including installation of ZNN and application to an image segmentation challenge (http://brainiac2.mit.edu/isbi_challenge/). Participants should bring their own laptops, and will require access to their own Linux machine. Participants are encouraged to install ZNN (https://github.com/seung-lab/znn-release) prior to the event, as well as the boost and fftw libraries. RSVP tosseung(a)princeton.edu, as food will be provided.

1 0

Colloquium Speaker Marc Levoy Mon Oct 20, 4:30pm
by Nicole E. Wagenblast 20 Oct '14

20 Oct '14

What Google Glass means for the future of photography Marc Levoy, Stanford University Monday, October 20, 4:30pm Computer Science 105 Although head-mounted cameras (and displays) are not new, Google Glass has the potential to make these devices commonplace. This has implications for the practice, art, and uses of photography. So what's different about doing photography with Glass? First, Glass doesn't work like a conventional camera; it's hands-free, point-of-view, always available, and instantly triggerable. Second, Glass facilitates different uses than a conventional camera: recording documents, making visual todo lists, logging your life, and swapping eyes with other Glass users. Third, Glass will be an open platform, unlike most cameras. This is not easy, because Glass is a heterogeneous computing platform, with multiple processors having different performance, efficiency, and programmability. The challenge is to invent software abstractions that allow control over the camera as well as access to these specialized processors. Finally, devices like Glass that are head-mounted and perform computational photography in real time have the potential to give wearers "superhero vision", like seeing in the dark, or magnifying subtle motion or changes. If such devices can also perform computer vision in real time and are connected to the cloud, then they can do face recognition, live language translation, and information recall. The hard part is not imagining these capabilities, but deciding which ones are feasible, useful, and socially acceptable. Marc Levoy is the VMware Founders Professor of Computer Science, Emeritus. Education: B. Architecture and M.S. from Cornell (1976,1978), PhD in Computer Science from University of North Carolina (1989). In previous lives he worked on computer-assisted cartoon animation (1970s), volume rendering (1980s), 3D scanning (1990s), and computational photography (2000s), including light field photography and microscopy. At Stanford he taught computer graphics, digital photography, and the science of art. Outside of academia, Levoy co-designed the Google book scanner, launched Google's Street View project, and currently leads a team in GoogleX working on Project Glass and the Nexus 5's HDR+ mode. Awards: Charles Goodwin Sands Medal for best undergraduate thesis (1976), National Science Foundation Presidential Young Investigator (1991), ACM SIGGRAPH Computer Graphics Achievement Award (1996), ACM Fellow (2007).

1 2

Postponed Colloquium Speaker Matthew Green
by Nicole E. Wagenblast 19 Oct '14

19 Oct '14

This even has been postponed. A new date/time will be announced as soon as the information becomes available. Decentralized Anonymous Credentials and Electronic Payments from Bitcoin Matthew Green, John Hopkins University Tuesday, October 21 , 4:30pm Computer Science 105 Traditionally, making statements about identity on the Internet, whether literal assertions of identity or statements about one’s identity, requires centralized providers who issue credentials attesting to the user’s information. These organizations, which include Certificate Authorities, DNS maintainers, or login providers like Google and Facebook, play a large role in securing internet infrastructure, email, and financial transactions. Our increasing reliance on these providers raises concerns about privacy and trust. Anonymous credentials represent a powerful solution to this privacy concern: they deprive even colluding credential issuers and verifiers of the ability to identify and track their users. Although credentials may involve direct assertions of identity, they may also be used for a large range of useful assertions, such as “my TPM says my computer is secure”, “I have a valid subscription for content”, or “I am eligible to vote.” Anonymous credentials can also be used as a basis for constructing untraceable electronic payment systems, or “e-cash". Unfortunately most existing anonymous credential and e-cash systems have a fundamental limitation: they require the appointment of a central, trusted party to issue credentials or tokens. This issuer represents a single point of failure and an obvious target for compromise. In distributed settings such as ad hoc or peer-to-peer networks, it may be challenging even to identify parties who can be trusted to play this critical role. In this talk I will discuss new techniques for building anonymous credentials and electronic cash in a fully decentralized setting. The basic ingredient of these proposals is a "distributed public append-only ledger", a technology which has most famously been deployed in digital currencies such as Bitcoin. This ledger can be employed by individual nodes to make assertions about a user’s attributes in a fully anonymous fashion — without the assistance of a credential issuer. One concrete result of these techniques is a new protocol named “Zerocash”, which adds cryptographically unlinkable electronic payments to the Bitcoin currency. Prof. Matthew Green is a Research Professor at the Johns Hopkins University Information Security Institute. His research focus is on cryptographic techniques for maintaining users’ privacy, and on technologies that enable the deployment of privacy-preserving protocols. From 2004-2011, Green served as CTO of Independent Security Evaluators, a custom security evaluation firm with a global client base. Along with a team at Johns Hopkins and RSA Laboratories, he discovered flaws in the Texas Instruments Digital Signature Transponder, a cryptographically-enabled RFID device used in the Exxon Speedpass payment system and in millions of vehicle immobilizers.

1 0

Colloquium Speaker Matthew Green Tues Oct 21, 4:30pm
by Nicole E. Wagenblast 17 Oct '14

17 Oct '14

Decentralized Anonymous Credentials and Electronic Payments from Bitcoin Matthew Green, John Hopkins University Tuesday, October 21 , 4:30pm Computer Science 105 Traditionally, making statements about identity on the Internet, whether literal assertions of identity or statements about one’s identity, requires centralized providers who issue credentials attesting to the user’s information. These organizations, which include Certificate Authorities, DNS maintainers, or login providers like Google and Facebook, play a large role in securing internet infrastructure, email, and financial transactions. Our increasing reliance on these providers raises concerns about privacy and trust. Anonymous credentials represent a powerful solution to this privacy concern: they deprive even colluding credential issuers and verifiers of the ability to identify and track their users. Although credentials may involve direct assertions of identity, they may also be used for a large range of useful assertions, such as “my TPM says my computer is secure”, “I have a valid subscription for content”, or “I am eligible to vote.” Anonymous credentials can also be used as a basis for constructing untraceable electronic payment systems, or “e-cash". Unfortunately most existing anonymous credential and e-cash systems have a fundamental limitation: they require the appointment of a central, trusted party to issue credentials or tokens. This issuer represents a single point of failure and an obvious target for compromise. In distributed settings such as ad hoc or peer-to-peer networks, it may be challenging even to identify parties who can be trusted to play this critical role. In this talk I will discuss new techniques for building anonymous credentials and electronic cash in a fully decentralized setting. The basic ingredient of these proposals is a "distributed public append-only ledger", a technology which has most famously been deployed in digital currencies such as Bitcoin. This ledger can be employed by individual nodes to make assertions about a user’s attributes in a fully anonymous fashion — without the assistance of a credential issuer. One concrete result of these techniques is a new protocol named “Zerocash”, which adds cryptographically unlinkable electronic payments to the Bitcoin currency. Prof. Matthew Green is a Research Professor at the Johns Hopkins University Information Security Institute. His research focus is on cryptographic techniques for maintaining users’ privacy, and on technologies that enable the deployment of privacy-preserving protocols. From 2004-2011, Green served as CTO of Independent Security Evaluators, a custom security evaluation firm with a global client base. Along with a team at Johns Hopkins and RSA Laboratories, he discovered flaws in the Texas Instruments Digital Signature Transponder, a cryptographically-enabled RFID device used in the Exxon Speedpass payment system and in millions of vehicle immobilizers.

1 0

Colloquium Speaker Yann LeCun Weds Oct 22, 4:30pm
by Nicole E. Wagenblast 16 Oct '14

16 Oct '14

Yann LeCun, Facebook AI Research and Center for Data Science, New York University The Unreasonable Effectiveness of Deep Learning Wednesday, October 22, 4:30pm Computer Science 105 The emergence of large datasets, parallel computers, and new machine learning methods, have enabled the deployment of highly-accurate computer perception systems and are opening the door to a wide deployment of AI systems. A key component in AI systems is a module, sometimes called a feature extractor, that turns raw inputs into suitable internal representations. But designing and building such a module requires a considerable amount of engineering efforts and domain expertise. Deep Learning methods have provided a way to automatically learn good representations of data from labeled or unlabeled samples. Deep architectures are composed of successive stages in which data representations are increasingly global, abstract, and invariant to irrelevant transformations of the input. Deep learning enables end-to-end training of these architectures, from raw inputs to ultimate outputs. The convolutional network model (ConvNet) is a particular type of deep architecture somewhat inspired by biology, which consists of multiple stages of filter banks, interspersed with non-linear operators, and spatial pooling. ConvNets have become the record holder for a wide variety of benchmarks, including object detection, localization and recognition in image, semantic segmentation and labeling, face recognition, acoustic modeling for speech recognition, drug design, handwriting recognition, biological image segmentation, etc. The most recent systems deployed by Facebook, Google, NEC, IBM, Microsoft, Baidu, Yahoo and others for image understanding, speech recognition, and natural language processing use deep learning. Many of these systems use very large and very deep ConvNets with billions of connections, trained in supervised mode. But many new applications require the use of unsupervised feature learning. A number of such methods based on sparse auto-encoder will be presented. Several applications will be shown through videos and live demos, including a category-level object recognition system that can be trained on the fly, a scene parsing system that can label every pixel in an image with the category of the object it belongs to (scene parsing), an object localization and detection system, and several natural language processing systems. Specialized hardware architectures that run these systems in real time will also be described. Yann LeCun is Director of AI Research at Facebook, and Silver Professor of Data Science, Computer Science, Neural Science, and Electrical Engineering at New York University, affiliated with the NYU Center for Data Science, the Courant Institute of Mathematical Science, the Center for Neural Science, and the Electrical and Computer Engineering Department. He received the Electrical Engineer Diploma from Ecole Supérieure d'Ingénieurs en Electrotechnique et Electronique (ESIEE), Paris in 1983, and a PhD in Computer Science from Université Pierre et Marie Curie (Paris) in 1987. After a postdoc at the University of Toronto, he joined AT&T Bell Laboratories in Holmdel, NJ in 1988. He became head of the Image Processing Research Department at AT&T Labs-Research in 1996, and joined NYU as a professor in 2003, after a brief period as a Fellow of the NEC Research Institute in Princeton. From 2012 to 2014 he directed NYU's initiative in data science and became the founding director of the NYU Center for Data Science. He was named Director of AI Research at Facebook in late 2013 and retains a part-time position on the NYU faculty. His current interests include AI, machine learning, computer perception, mobile robotics, and computational neuroscience. He has published over 180 technical papers and book chapters on these topics as well as on neural networks, handwriting recognition, image processing and compression, and on dedicated circuits and architectures for computer perception. The character recognition technology he developed at Bell Labs is used by several banks around the world to read checks and was reading between 10 and 20% of all the checks in the US in the early 2000s. His image compression technology, called DjVu, is used by hundreds of web sites and publishers and millions of users to access scanned documents on the Web. Since the mid 1980's he has been working on deep learning methods, particularly the convolutional network model, which is the basis of many products and services deployed by companies such as Facebook, Google, Microsoft, Baidu, IBM, NEC, AT&T and others for image and video understanding, document recognition, human-computer interaction, and speech recognition. LeCun has been on the editorial board of IJCV, IEEE PAMI, and IEEE Trans. Neural Networks, was program chair of CVPR'06, and is chair of ICLR 2013 and 2014. He is on the science advisory board of Institute for Pure and Applied Mathematics, and Neural Computation and Adaptive Perception Program of the Canadian Institute for Advanced Research. He has advised many large and small companies about machine learning technology, including several startups he co-founded. He is the lead faculty at NYU for the Moore-Sloan Data Science Environment, a $36M initiative in collaboration with UC Berkeley and University of Washington to develop data-driven methods in the sciences. He is the recipient of the 2014 IEEE Neural Network Pioneer Award.

1 0

Colloquium Speaker Trevor Darrell Today 4:30pm
by Nicole E. Wagenblast 16 Oct '14

16 Oct '14

Large-Scale Detector Adaptation and Other Recent Results Trevor Darrell , University of California, Berkeley Thursday, October 16, 4:30pm Computer Science 105 In this talk I'll review recent progress towards robust and effective perceptual representation learning. I'll describe new methods for large-scale detection, whereby robust detectors can be learned from weakly labeled training data, following paradigms of domain adaptation and multiple instance learning. I'll discuss how such models can be used not only for detection but also for pose prediction and further for effective fine-grained recognition, extending traditional convolutional neural network models to include explicit pose-normalized descriptors. Finally, and time permitting (pardon the pun), I'll review our recent work on anytime recognition, which provides methods that strive to provide the best answer possible, even with a limited (and unknown) time budget. Prof. Trevor Darrell’s group is co-located at the University of California, Berkeley, and the UCB-affiliated International Computer Science Institute (ICSI), also located in Berkeley, CA. Prof. Darrell is on the faculty of the CS Division of the EECS Department at UCB and is the vision group lead at ICSI. Darrell’s group develops algorithms for large-scale perceptual learning, including object and activity recognition and detection, for a variety of applications including multimodal interaction with robots and mobile devices. His interests include computer vision, machine learning, computer graphics, and perception-based human computer interfaces. Prof. Darrell was previously on the faculty of the MIT EECS department from 1999-2008, where he directed the Vision Interface Group. He was a member of the research staff at Interval Research Corporation from 1996-1999, and received the S.M., and PhD. degrees from MIT in 1992 and 1996, respectively. He obtained the B.S.E. degree from the University of Pennsylvania in 1988, having started his career in computer vision as an undergraduate researcher in Ruzena Bajcsy's GRASP lab.

1 0

Colloquium Speaker Trevor Darrell Thurs Oct 16, 4:30pm
by Nicole E. Wagenblast 15 Oct '14

15 Oct '14

Large-Scale Detector Adaptation and Other Recent Results Trevor Darrell , University of California, Berkeley Thursday, October 16, 4:30pm Computer Science 105 In this talk I'll review recent progress towards robust and effective perceptual representation learning. I'll describe new methods for large-scale detection, whereby robust detectors can be learned from weakly labeled training data, following paradigms of domain adaptation and multiple instance learning. I'll discuss how such models can be used not only for detection but also for pose prediction and further for effective fine-grained recognition, extending traditional convolutional neural network models to include explicit pose-normalized descriptors. Finally, and time permitting (pardon the pun), I'll review our recent work on anytime recognition, which provides methods that strive to provide the best answer possible, even with a limited (and unknown) time budget. Prof. Trevor Darrell’s group is co-located at the University of California, Berkeley, and the UCB-affiliated International Computer Science Institute (ICSI), also located in Berkeley, CA. Prof. Darrell is on the faculty of the CS Division of the EECS Department at UCB and is the vision group lead at ICSI. Darrell’s group develops algorithms for large-scale perceptual learning, including object and activity recognition and detection, for a variety of applications including multimodal interaction with robots and mobile devices. His interests include computer vision, machine learning, computer graphics, and perception-based human computer interfaces. Prof. Darrell was previously on the faculty of the MIT EECS department from 1999-2008, where he directed the Vision Interface Group. He was a member of the research staff at Interval Research Corporation from 1996-1999, and received the S.M., and PhD. degrees from MIT in 1992 and 1996, respectively. He obtained the B.S.E. degree from the University of Pennsylvania in 1988, having started his career in computer vision as an undergraduate researcher in Ruzena Bajcsy's GRASP lab.

1 0

Colloquium Speaker Alex Halderman- Wed Oct 15, 4:30pm
by Nicole E. Wagenblast 15 Oct '14

15 Oct '14

Colloquium Speaker J. Alex Halderman, University of Michigan Wednesday, October 15, 4:30pm Computer Science 105 The Internet's size, and the diversity of connected hosts, create difficult challenges for security. Conventionally, most vulnerabilities are discovered through labor-intensive scrutiny of individual implementations, but this scales poorly, and important classes of vulnerabilities can be hard to detect when considering hosts in isolation. Moreover, the security of the Internet as a whole is affected by management decisions made by individual system operators, but it is difficult to make sense of these choices--or to influence them to improve security--without a global perspective. In recent work, I have been developing new approaches to these challenges, based on the analysis of large-scale Internet measurement data. By collecting and analyzing the public keys used for HTTPS and SSH, my team discovered serious weaknesses in key generation affecting millions of machines, and we were able to efficiently factor the RSA moduli used by almost 0.5% of all HTTPS servers. By clustering and investigating the vulnerable hosts, we exposed flawed cryptographic implementations in network devices manufactured by more than 60 companies and uncovered a critical design flaw in the Linux kernel. To help other researchers apply similar techniques, we developed ZMap, a tool for performing Internet-wide network surveys that can probe the entire IPv4 address space in minutes, thousands of times faster than prior approaches. ZMap has become a thriving open-source project and is available in major Linux distributions. We've used it to develop defenses against compromised HTTPS certificate authorities, to study the Internet's response to the infamous OpenSSL Heartbleed vulnerability, and to significantly increase the global rate of patching for vulnerable hosts. Ultimately, measurement-driven approaches to Internet security may help shift the security balance of power to favor defenders over attackers. J. Alex Halderman is an assistant professor of computer science and engineering at the University of Michigan and director of Michigan's Center for Computer Security and Society. His research focuses on computer security and privacy, with an emphasis on problems that broadly impact society and public policy. Prof. Halderman's interests include application security, network security, anonymous and censorship-resistant communication, electronic voting, digital rights management, mass surveillance, and online crime, as well as the interaction of technology with law, regulatory policy, and international affairs. Prof. Halderman is widely known for developing the "cold boot" attack against disk encryption, which altered widespread security assumptions about the behavior of RAM, influenced computer forensics practice, and inspired the creation of a new subfield of theoretical cryptography. A noted expert on electronic voting security, he helped lead the first independent review of the election technology used by half a billion voters in India, which prompted the national government to undertake major technical reforms. He has authored more than 50 publications, and his work has won numerous distinctions, including two best paper awards from Usenix Security, a top systems security venue.

1 2