- talks - lists.cs.princeton.edu

Colloquium Speaker: Song Han- Monday, April 3- 4:30pm
by Nicole E. Wagenblast 29 Mar '17

29 Mar '17

Computer Science and Electrical Engineering Colloquium Speaker Song Han, Stanford University Monday, April 3, 4:30pm Computer Science 105 Host: Prof. Kai Li and Prof. David Wentzlaff Efficient Methods and Hardware for Deep Learning Deep learning has spawned a wide range of AI applications that are changing our lives. However, deep neural networks are both computationally and memory intensive, thus they are power hungry when deployed on embedded systems and data centers with a limited power budget. To address this problem, I will present an algorithm and hardware co-design methodology for improving the efficiency of deep learning. I will first introduce "Deep Compression", which can compress deep neural network models by 10–49× without loss of prediction accuracy for a broad range of CNN, RNN, and LSTMs. The compression reduces both computation and storage. Next, by changing the hardware architecture and efficiently implementing Deep Compression, I will introduce EIE, the Efficient Inference Engine, which can perform decompression and inference simultaneously, saving a significant amount of memory bandwidth. By taking advantage of the compressed model and being able to deal with an irregular computation pattern efficiently, EIE achieves 13× speedup and 3000× better energy efficiency over GPU. Finally, I will revisit the inefficiencies in current learning algorithms, present DSD training, and discuss the challenges and future work in efficient methods and hardware for deep learning. Song Han is a Ph.D. candidate supervised by Prof. Bill Dally at Stanford University. His research focuses on energy-efficient deep learning, at the intersection between machine learning and computer architecture. He proposed the Deep Compression algorithm, which can compress neural networks by 10–49× while fully preserving prediction accuracy. He designed the first hardware accelerator that can perform inference directly on a compressed sparse model, which results in significant speedup and energy saving. His work has been featured by O’Reilly, TechEmergence, TheNextPlatform, and Embedded Vision, and it has impacted the industry. He led research efforts in model compression and hardware acceleration that won the Best Paper Award at ICLR’16 and the Best Paper Award at FPGA’17. Before joining Stanford, Song graduated from Tsinghua University.

1 0

Colloquium Speaker: David Held, Thursday March 29, 12:30pm- reminder
by Nicole E. Wagenblast 29 Mar '17

29 Mar '17

Colloquium Speaker Dr. David Held, University of California, Berkeley Thursday, March 30- 12:30pm Computer Science 105 Host: Prof. Tom Funkhouser Robots in Clutter: Learning to Understand Environmental Changes Robots today are confined to operate in relatively simple, controlled environments. One reason for this is that current methods for processing visual data tend to break down when faced with occlusions, viewpoint changes, poor lighting, and other challenging but common situations that occur when robots are placed in the real world. I will show that we can train robots to handle these variations by modeling the causes behind visual appearance changes. If robots can learn how the world changes over time, they can be robust to the types of changes that objects often undergo. I demonstrate this idea in the context of autonomous driving, and I will show how we can use this idea to improve performance for every step of the robotic perception pipeline: object segmentation, tracking, and velocity estimation. I will also present some recent work on learning to manipulate objects, using a similar framework of learning environmental changes. By learning how the environment can change over time, we can enable robots to operate in the complex, cluttered environments of our daily lives. David Held is a post-doctoral researcher at U.C. Berkeley working with Pieter Abbeel on deep reinforcement learning for robotics. He recently completed his Ph.D. in Computer Science at Stanford University with Sebastian Thrun and Silvio Savarese, where he developed methods for perception for autonomous vehicles. David has also worked as an intern on Google’s self-driving car team. Before Stanford, David was a researcher at the Weizmann Institute, where he worked on building a robotic octopus. He received a B.S. and M.S. in Mechanical Engineering at MIT and an M.S. in Computer Science at Stanford, for which he was awarded the Best Master's Thesis Award from the Computer Science Department.

1 0

Colloquium Speaker: Ali José Mashtizadeh, Today- 12:30pm
by Nicole E. Wagenblast 28 Mar '17

28 Mar '17

Colloquium Speaker Ali José Mashtizadeh, Stanford University Tuesday, March 28- 12:30pm Computer Science 105 Host: Prof. Michael Freedman Systems and Tools for Reliable Software: Replication, Reproducibility, and Security The past decade has seen a rapid acceleration in the development of new and transformative applications in many areas including transportation, medicine, ﬁnance, and communication. Most of these applications are made possible by the increasing diversity and scale of hardware and software systems. While this brings unprecedented opportunity, it also increases the probability of failures and the difﬁculty of diagnosing them. Increased scale and transience has also made management increasingly challenging. Devices can come and go for a variety of reasons including mobility, failure and recovery, and scaling capacity to meet demand. In this talk, I will be presenting several systems that I built to address the resulting challenges to reliability, management, and security. Ori is a reliable distributed ﬁle system for devices at the network edge. Ori automates many of the tasks of storage reliability and recovery through replication, taking advantage of fast LANs and low cost local storage in edge networks. Castor is record/replay system for multi-core applications with predictable and consistently low overheads. This makes it practical to leave record/replay on in production systems, to reproduce difficult bugs when they occur, and to support recovering from hardware failures through fault tolerance. Cryptographic CFI (CCFI) is a dynamic approach to control flow integrity. Unlike previous CFI systems that rely purely on static analysis, CCFI can classify pointers based on dynamic and runtime characteristics. This limits the attacks to only actively used code paths, resulting in a substantially smaller attack surface. Ali is currently completing his PhD at Stanford University where he is advised by Prof. David Mazières. His work focuses on improving reliability, ease of management and security in operating systems and distributed systems. Previously, he was a Staff Engineer at VMware, Inc. where he was the technical lead for the live migration products. Ali received an M.Eng. in electrical engineering and computer science and a B.S. in electrical engineering from the Massachusetts Institute of Technology.

1 0

Bogdan Pasaniuc Special Seminar - tomorrow at LSI
by Nicole E. Wagenblast 27 Mar '17

27 Mar '17

Please note, special seminar at LSI tomorrow! Tuesday, March 28 th at 10:00 a.m. in Icahn 280 Special Seminar with Bogdan Pasaniuc, Ph.D., University of California Los Angeles “ Integrating eQTL and GWAS to identify genes associated to complex traits". Abstract: Many complex traits and diseases share a correlation at a phenotypic level. Such correlations can be attributed to shared environmental or genetic architectures. Quantifying the correlation in phenotypes that is due to genetics is of great interest in understanding the causal relationship between traits. Here I present new methods for estimation of local genetic variance/covariance and discuss their relationship with the recently proposed methods for gene expression prediction as a tool to integrate eQTL and GWAS to identify genes associated to complex traits.

1 0

Colloquium Speaker: Ali José Mashtizadeh, Tuesday, March 28- 12:30pm-reminder
by Nicole E. Wagenblast 27 Mar '17

27 Mar '17

Colloquium Speaker Ali José Mashtizadeh, Stanford University Tuesday, March 28- 12:30pm Computer Science 105 Host: Prof. Michael Freedman Systems and Tools for Reliable Software: Replication, Reproducibility, and Security The past decade has seen a rapid acceleration in the development of new and transformative applications in many areas including transportation, medicine, ﬁnance, and communication. Most of these applications are made possible by the increasing diversity and scale of hardware and software systems. While this brings unprecedented opportunity, it also increases the probability of failures and the difﬁculty of diagnosing them. Increased scale and transience has also made management increasingly challenging. Devices can come and go for a variety of reasons including mobility, failure and recovery, and scaling capacity to meet demand. In this talk, I will be presenting several systems that I built to address the resulting challenges to reliability, management, and security. Ori is a reliable distributed ﬁle system for devices at the network edge. Ori automates many of the tasks of storage reliability and recovery through replication, taking advantage of fast LANs and low cost local storage in edge networks. Castor is record/replay system for multi-core applications with predictable and consistently low overheads. This makes it practical to leave record/replay on in production systems, to reproduce difficult bugs when they occur, and to support recovering from hardware failures through fault tolerance. Cryptographic CFI (CCFI) is a dynamic approach to control flow integrity. Unlike previous CFI systems that rely purely on static analysis, CCFI can classify pointers based on dynamic and runtime characteristics. This limits the attacks to only actively used code paths, resulting in a substantially smaller attack surface. Ali is currently completing his PhD at Stanford University where he is advised by Prof. David Mazières. His work focuses on improving reliability, ease of management and security in operating systems and distributed systems. Previously, he was a Staff Engineer at VMware, Inc. where he was the technical lead for the live migration products. Ali received an M.Eng. in electrical engineering and computer science and a B.S. in electrical engineering from the Massachusetts Institute of Technology.

1 0

Colloquium Speaker: Zakir Durumeric, Today, 12:30pm
by Nicole E. Wagenblast 27 Mar '17

27 Mar '17

Colloquium Speaker Zakir Durumeric, University of Michigan Monday, March 27- 12:30pm Computer Science 105 Host: Prof. Arvind Narayanan Data-Driven Security For too long, computer science has approached security in an ad hoc and reactionary manner. In order to make meaningful progress, we need to shift our defensive approach to be data-driven and epidemiological. Over the course of my Ph.D., I have built systems to facilitate a data-driven approach to security, and I have applied this methodology to tackle some of the most pressing real-world security problems. In this talk, I will first highlight two of these systems, ZMap and Censys. Second, I will show how Internet-wide scanning has enabled us to identify weaknesses in cryptographic keys, uncover real-world attacks against email delivery, and guide users in patching vulnerabilities. I will conclude by discussing how, in the future, I want to elevate data-driven security beyond individual systems and tools to make it a fundamental part of the Internet ecosystem. Zakir Durumeric is a Ph.D. Candidate and Google Research Fellow in Computer Science and Engineering at the University of Michigan where his research focuses on systems and network security. His work has received the IRTF Applied Networking Research Prize and best paper awards from USENIX Security, ACM CCS, and ACM IMC.

1 0

Colloquium Speaker: Zakir Durumeric, Monday March 27, 12:30pm-reminder
by Nicole E. Wagenblast 26 Mar '17

26 Mar '17

Colloquium Speaker Zakir Durumeric, University of Michigan Monday, March 27- 12:30pm Computer Science 105 Host: Prof. Arvind Narayanan Data-Driven Security For too long, computer science has approached security in an ad hoc and reactionary manner. In order to make meaningful progress, we need to shift our defensive approach to be data-driven and epidemiological. Over the course of my Ph.D., I have built systems to facilitate a data-driven approach to security, and I have applied this methodology to tackle some of the most pressing real-world security problems. In this talk, I will first highlight two of these systems, ZMap and Censys. Second, I will show how Internet-wide scanning has enabled us to identify weaknesses in cryptographic keys, uncover real-world attacks against email delivery, and guide users in patching vulnerabilities. I will conclude by discussing how, in the future, I want to elevate data-driven security beyond individual systems and tools to make it a fundamental part of the Internet ecosystem. Zakir Durumeric is a Ph.D. Candidate and Google Research Fellow in Computer Science and Engineering at the University of Michigan where his research focuses on systems and network security. His work has received the IRTF Applied Networking Research Prize and best paper awards from USENIX Security, ACM CCS, and ACM IMC.

1 0

Colloquium Speaker: Zakir Durumeric, Monday March 27, 12:30pm
by Nicole E. Wagenblast 21 Mar '17

21 Mar '17

Colloquium Speaker Zakir Durumeric, University of Michigan Monday, March 27- 12:30pm Computer Science 105 Host: Prof. Arvind Narayanan Data-Driven Security For too long, computer science has approached security in an ad hoc and reactionary manner. In order to make meaningful progress, we need to shift our defensive approach to be data-driven and epidemiological. Over the course of my Ph.D., I have built systems to facilitate a data-driven approach to security, and I have applied this methodology to tackle some of the most pressing real-world security problems. In this talk, I will first highlight two of these systems, ZMap and Censys. Second, I will show how Internet-wide scanning has enabled us to identify weaknesses in cryptographic keys, uncover real-world attacks against email delivery, and guide users in patching vulnerabilities. I will conclude by discussing how, in the future, I want to elevate data-driven security beyond individual systems and tools to make it a fundamental part of the Internet ecosystem. Zakir Durumeric is a Ph.D. Candidate and Google Research Fellow in Computer Science and Engineering at the University of Michigan where his research focuses on systems and network security. His work has received the IRTF Applied Networking Research Prize and best paper awards from USENIX Security, ACM CCS, and ACM IMC.

1 0

Colloquium Speaker: Ali José Mashtizadeh, Tuesday, March 28- 12:30pm- reminder
by Nicole E. Wagenblast 21 Mar '17

21 Mar '17

Colloquium Speaker Ali José Mashtizadeh, Stanford University Tuesday, March 28- 12:30pm Computer Science 105 Host: Prof. Michael Freedman Systems and Tools for Reliable Software: Replication, Reproducibility, and Security The past decade has seen a rapid acceleration in the development of new and transformative applications in many areas including transportation, medicine, ﬁnance, and communication. Most of these applications are made possible by the increasing diversity and scale of hardware and software systems. While this brings unprecedented opportunity, it also increases the probability of failures and the difﬁculty of diagnosing them. Increased scale and transience has also made management increasingly challenging. Devices can come and go for a variety of reasons including mobility, failure and recovery, and scaling capacity to meet demand. In this talk, I will be presenting several systems that I built to address the resulting challenges to reliability, management, and security. Ori is a reliable distributed ﬁle system for devices at the network edge. Ori automates many of the tasks of storage reliability and recovery through replication, taking advantage of fast LANs and low cost local storage in edge networks. Castor is record/replay system for multi-core applications with predictable and consistently low overheads. This makes it practical to leave record/replay on in production systems, to reproduce difficult bugs when they occur, and to support recovering from hardware failures through fault tolerance. Cryptographic CFI (CCFI) is a dynamic approach to control flow integrity. Unlike previous CFI systems that rely purely on static analysis, CCFI can classify pointers based on dynamic and runtime characteristics. This limits the attacks to only actively used code paths, resulting in a substantially smaller attack surface. Ali is currently completing his PhD at Stanford University where he is advised by Prof. David Mazières. His work focuses on improving reliability, ease of management and security in operating systems and distributed systems. Previously, he was a Staff Engineer at VMware, Inc. where he was the technical lead for the live migration products. Ali received an M.Eng. in electrical engineering and computer science and a B.S. in electrical engineering from the Massachusetts Institute of Technology.

1 0

Lecture by Mahzarin Banaji (Harvard): "Blindspot: Hidden Biases of Good People" (4:30pm Apr 13, McCosh 50)
by Scott Karlin 18 Mar '17

18 Mar '17

BLINDSPOT: HIDDEN BIASES OF GOOD PEOPLE Introduction by DEBORAH A. PRENTICE Dean of the Faculty, Alexander Stewart 1886 Professor of Psychology and Public Affairs Keynote by MAHZARIN BANAJI Richard Clarke Cabot Professor of Social Ethics, Harvard University, Department of Psychology Mahzarin Banaji studies unconscious thinking and feeling as they unfold in social group contexts and influence decisions about people’s worth, goodness, and competence. She is the author of the best-selling book Blindspot: Hidden Biases of Good People with Anthony Greenwald, published by Random House. This lecture is participatory, involving educational and even entertaining interactive exercises. It is geared toward providing insights into how our minds work, often in a surprising and even perplexing manner. Professor Banaji will speak to the question of how well-intentioned people behave in ways that deviate from their own values and principles, and how this state of affairs compromises decisions in the social context: decisions about a person’s worth and competence as it plays out in public settings whether it be schools, the workplace, or the street. The purpose of the lecture is to reveal mental blindspots that can compromise our professional and personal decisions if they are left unattended and to begin a conversation about what might be done to allow us to lead the examined life we aspire to. APRIL 13, 2017, 4:30PM, MCCOSH 50

1 0