PPT-Deep Transfer Learning and Multi-task Learning

Transfer Learning Transfer a model trained on source data A to target data B Task transfer in this case the source and target data can be the same Image classification gt image segmentation. Quoc V. Le. Stanford University and Google. Purely supervised. Quoc V. . Le. Almost abandoned between 2000-2006. - . Overfitting. , slow, many local minima, gradient vanishing. In 2006, Hinton, et. al. proposed RBMs to . Early Work. Why Deep Learning. Stacked Auto Encoders. Deep Belief Networks. CS 678 – Deep Learning. 1. Deep Learning Overview. Train networks with many layers (vs. shallow nets with just a couple of layers). Carey . Nachenberg. Deep Learning for Dummies (Like me) – Carey . Nachenberg. (Like me). The Goal of this Talk?. Deep Learning for Dummies (Like me) – Carey . Nachenberg. 2. To provide you with . The End of the Joan of Arc . Teacher Recruitment Strategy. BEST-NC Innovation Lab. September 28, 2016. Cary, NC. Southern Regional Education Board. Andy Baxter, Vice President for Educator Effectiveness. Original Words by Samuel Trevor Francis (1834-1925). Music, chorus, and alternate words by Bob Kauflin.. © 2008 Integrity’s Praise! Music/Sovereign Grace Praise (BMI). Sovereign Grace Music, a division of Sovereign Grace Ministries.. Transfer Learning. Dog/Cat. Classifier. cat. dog. Data . not directly related to . the task considered. elephant. tiger. Similar domain, different tasks. Different domains, same task. http://weebly110810.weebly.com/396403913129399.html. Rajdeep. . Dasgupta. CIDER Community Workshop, CA. May 08, 2016. Volcanic degassing. hazards. long-term climate. Bio-essential elements. Origin of life. Mantle melting. Chemical differentiation. Properties of asthenosphere. CS 501:CS Seminar. Min Xian. Assistant Professor. Department of Computer Science. University of Idaho. Image from NVIDIA. Researchers:. Geoff Hinton. Yann . LeCun. Andrew Ng. Yoshua. . Bengio. …. Topic 3. 4/15/2014. Huy V. Nguyen. 1. outline. Deep learning overview. Deep v. shallow architectures. Representation learning. Breakthroughs. Learning principle: greedy layer-wise training. Tera. . scale: data, model, . Transfer Learning CS 294 - 112: Deep Reinforcement Learning Sergey Levine Class Notes 1. Homework 4 due today! Last one! Recap: classes of exploration methods in deep RL • Optimistic exploration: Generative Adversarial Networks (GANs). Generative Adversarial Networks (GANs). Goodfellow. et al (2014) . https://arxiv.org/abs/1406.2661. Minimize distance between the distributions of real data and generated samples. Sushmita Roy. sroy@biostat.wisc.edu. Computational Network Biology. Biostatistics & Medical Informatics 826. https://compnetbiocourse.discovery.wisc.edu. Oct 23. rd. . 2018. Strategies for capturing dynamics in networks. Chair for Computer Aided Medical Procedures & Augmented Reality. Master seminar: Deep Learning for Medical Applications. Tutor: . Shadi. . Albarqouni. , PhD. Student: Panarit Jahiri. Maithra. Raghu, . Patient Cohort Retrieval . Sanda. . Harabagiu. , . PhD. , Travis Goodwin, Ramon Maldonado, Stuart Taylor . The . Human Language Technology Research Institute. University of Texas at Dallas. Human Language Technology.