Select a calendar:
Filter May Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for May 08, 2018
-
Six Sigma Green Belt for Process ImprovementTue, May 08, 2018
Executive Education
Conferences, Lectures, & Seminars
Abstract: Learn how to integrate principles of business, statistics, and engineering to achieve tangible results. Master the use of Six Sigma to quantify the critical quality issues in your company. Once the issues have been quantified, statistics can be applied to provide probabilities of success and failure. Six Sigma methods increase productivity and enhance quality.
More Info: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/
Audiences: Registered Attendees
Contact: Corporate & Professional Programs
-
PhD Defense - Xing Shi
Tue, May 08, 2018 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Xing Shi
Date: May 8, 10am at SAL 322
Committee: Kevin Knight (chair), Jonathan May and Shri Narayanan
Abstract:
Recurrent neural networks (RNN) have been successfully applied to various Natural Language Processing tasks, including language modeling, machine translation, text generation, etc. However, several obstacles still stand in the way: First, due to the RNN's distributional nature, few interpretations of its internal mechanism are obtained, and it remains a black box. Second, because of the large vocabulary sets involved, the text generation is very time-consuming. Third, there is no flexible way to constrain the generation of the sequence model with external knowledge. Last, huge training data must be collected to guarantee the performance of these neural models, whereas annotated data such as parallel data used in machine translation are expensive to obtain. This work aims to address the four challenges mentioned above.
To further understand the internal mechanism of the RNN, we choose neural machine translation (NMT) systems as a testbed. We first investigate how NMT outputs target strings of appropriate lengths, locating a collection of hidden units that learns to explicitly implement this functionality. Then we investigate whether NMT systems learn source language syntax as a by-product of training on string pairs. We find that both local and global syntactic information about source sentences is captured by the encoder. Different types of syntax are stored in different layers, with different concentration degrees.
To speed up text generation, we propose two novel GPU-based algorithms: 1) Utilize the source/target words alignment information to shrink the target side run-time vocabulary; 2) Apply locality sensitive hashing to find nearest word embeddings. Both methods lead to a 2-3x speedup on four translation tasks without hurting machine translation accuracy as measured by BLEU. Furthermore, we integrate a finite state acceptor into the neural sequence model during generation, providing a flexible way to constrain the output, and we successfully apply this to poem generation, in order to control the meter and rhyme.
To improve NMT performance on low-resource language pairs, we re-examine multiple technologies that are used in high resource language NMT and other NLP tasks, explore their variations and result in a strong NMT system for low resource languages. Experiments on Uygher-English shows a 10+ BLEU score improvement over the vanilla NMT system.
Location: Henry Salvatori Computer Science Center (SAL) - 322
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Defense- Soravit (Beer) Changpinyo
Tue, May 08, 2018 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Soravit (Beer) Changpinyo
Committee: Fei Sha (chair), Kevin Knight, C.-C. Jay Kuo (outside member)
Title: Modeling, Learning, and Leveraging Similarity
Time & Place: Tuesday, May 8th, 12-2pm, SAL 213
Abstract:
Measuring similarity between any two entities is an essential component in most machine learning tasks. In this defense, I will describe my research work that provides a set of techniques revolving around the notion of similarity.
The first part involves "modeling and learning" similarity. We introduce Similarity Component Analysis (SCA), a Bayesian network for modeling instance-level similarity that does not observe the triangle inequality. Such a modeling choice avoids the transitivity bias in most existing similarity models, making SCA intuitively more aligned with the human perception of similarity.
The second part involves "learning and leveraging" similarity for effective learning with limited data, with applications in computer vision and natural language processing. We first leverage incomplete and noisy similarity graphs in different modalities to aid the learning of object recognition models. In particular, we propose two novel zero-shot learning algorithms that utilize class-level semantic similarities as a building block, establishing state-of-the-art performance on the large-scale benchmark with more than 20,000 categories. As for natural language processing, we employ multi-task learning (MTL) to leverage unknown similarities between sequence tagging tasks. This study leads to insights regarding the benefit of going to beyond pairwise MTL, task selection strategies, as well as the nature of the relationships between those tasks.
Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Defense - Sayan Ghosh
Tue, May 08, 2018 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title : Multimodal Representation Learning of Affective Behavior
PhD Candidate: Sayan Ghosh
Date : 8th May , 2 PM PST
Venue: PHE 223
Committee : Prof. Stefan Scherer (Chair), Prof. Louis-Philippe Morency, Prof. Kevin Knight, Prof. Panayiotis Georgiou (EE)
Abstract:
With the ever increasing abundance of multimedia data available on the Internet and crowd-sourced datasets/repositories, there has been a renewed interest in machine learning approaches for solving real-life perception problems. However, such techniques have only recently made inroads into research problems relevant to the study of human emotion and behavior understanding. The primary research challenges addressed in this defense talk pertain to unimodal and multimodal representation learning, and the fusion of emotional and non-verbal cues for language modeling . There are three primary contributions of this dissertation -
(1) Unimodal Representation Learning: In the visual modality a novel multi-label CNN (Convolutional Neural Network) is proposed for learning AU (Action Unit) occurrences in facial images. The multi-label CNN learns a joint representation for AU occurrences, obtaining competitive detection results; and is also robust across different datasets. For the acoustic modality, denoising autoencoders and RNNs (Recurrent Neural Networks) are trained on temporal frames from speech spectrograms, and it is observed that representation learning from the glottal flow signal (the component of the speech signal with vocal tract influence removed) can be applied to speech emotion recognition.
(2) Multimodal Representation Learning: An importance-based multimodal autoencoder (IMA) model is introduced which can learn joint multimodal representations as well as importance weights for each modality. The IMA model achieves performance improvement relative to baseline approaches for the tasks of digit recognition and emotion understanding from spoken utterances.
(3) Non-verbal and Affective Language Models: This dissertation studies deep multimodal fusion in the context of neural language modeling by introducing two novel approaches - Affect-LM and Speech-LM. These models obtain perplexity reductions over a baseline language model by integrating verbal affective and non-verbal acoustic cues with the linguistic context for predicting the next word. Affect-LM also generates text in different emotions at various levels of intensity. The generated sentences are emotionally expressive while maintaining grammatical correctness as evaluated through a crowd-sourced perception study.
Location: Charles Lee Powell Hall (PHE) - 223
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
INCOSE-LA Speaker Meeting
Tue, May 08, 2018 @ 05:15 PM - 07:30 PM
Systems Architecting and Engineering, USC Viterbi School of Engineering
Conferences, Lectures, & Seminars
Speaker: Kay Das, INCOSE - Los Angeles
Talk Title: The Connected Vehicle Revolution - Continued
Series: INCOSE-LA Speaker Series
Abstract: The second installment of our light-hearted but critical look at the Connected Vehicle revolution. There is currently much ongoing activity in the research and design of systems to enhance the safety of vehicular traffic on roads and highways. These include vehicle-to-vehicle based and vehicle-to-infrastructure based electronics systems with extension to personal devices. These systems need to work collaboratively in an intelligent and reconfigurable network environment characterized by multiple localized and dynamically changing motion control loops which include each individual vehicle driver (and pedestrian). Systems will comprise a mix of existing and new technologies such as laser, imaging, computer vision, radar, cellular, WiFi, GPS, millimetric Waves, and others. System complexity is very high to deliver and sustain the required levels of reliability. A range of products and systems will compete for market entry from diverse developers and nations. Compliance with a safety culture within product development, such as directed by the ISO 26262 cocoon, is desirable. Safety needs to be regarded as an integral and critical element in system, software, hardware, and device and sensor design. A significant challenge also exists in validating prototypes and final systems productized for market entry. The cost of failure is high as human life is in the loop. This presentation reviews some of the challenges and offers some directions for this burgeoning industry propelled by developments ranging from Shannons Law and Moores Law to the evolving Internet of Things and 5G cellular communications. Management of systems research and development with frugality, without over-design, and with a holistic approach on a scale probably never demanded before, is required.
RSVP: Required, see the event link below.
WHERE: Rockwell Collins - Irvine
1733 Alton Pkwy,
Irvine, CA 92606
Host: Andrew Murrell
Phone: 714-929-3503
When you arrive please wait in the Rockwell Collins Lobby in Building 18 (A Rockwell Collins sign will be on the building) and check in with Security, you will need to present identification and a visitor badge will be issued. A Rockwell Employee will then escort you to the Conference room.
COST: INCOSE Members: FREE. Non-members: $10 (refreshments provided)
SCHEDULE:
5:15-5:30 Sign-in and Registration
5:30-6:00 Networking and Refreshments
6:10-6:20 Introduction
6:20-6:30 WG Presentation (TBD)
6:30-7:30 Guest Speaker Presentation
Biography: Kay Das was GPS Program Manager and Technical Director at LinQuest Corporation in Los Angeles from 2007 to 2013 where he additionally led new business development thrusts in the commercial and automotive safety markets. He has previously held responsibilities as R&D Director for STMicroelectronics Asia Pacific region. He is a winner of a Singapore Government National Award for The Initiation and Expansion of High-value R&D and Promotion of Partnerships. He has built and led teams in different parts of the world and managed the development of diverse silicon-based signal processing systems over 40 years in industry. His current pursuits are the application of communication (such as 5G-DSRC) and location technologies (such as GPS-GNSS) to the Connected Vehicle revolution. He holds an MS in Electronics Systems from the Cranfield Institute of Technology, UK. His pursuits in retirement other than Connected Vehicle include amateur astronomy, Internet radio, and he is a professional musician. He is an IEEE Life Member and a member of several societies.
Host: International Council on Systems Engineering (INCOSE)
More Info: http://events.r20.constantcontact.com/register/event?llr=l4ihvgeab&oeidk=a07ef7zwisr1ddb5ba8
Location: Rockwell Collins - Irvine
Audiences: Everyone Is Invited
Contact: Deborah A. Cannon
Event Link: http://events.r20.constantcontact.com/register/event?llr=l4ihvgeab&oeidk=a07ef7zwisr1ddb5ba8
