Schedule
This is a tentative schedule and may change slightly.
Date | Paper | Slides, Paper, Project page | Presenter |
Thurs, Jan 19 | Brief History of Visual Classification | slides | |
Tues, Jan 24 | Intro to Image Classification | slides, Python tutorial, Image Classification Notes, Linear Classification Notes | |
Thurs, Jan 26 | Linear Classification: loss functions, optimization, gradient descent | slides, svm, softmax notes,optimization | |
Tues, Jan 31 | Neural Nets: Backpropagation and Computational (Chain rule) Graphs | slides | |
Thurs, Feb 2 | Assignment #1 Due | ||
Thurs, Feb 2 | Training Neural Nets I: activation functions, weight initialization, hyperparameter optimization | slides, Neural Net Notes 1, Practical recommendations from Yoshua Bengio, and some other SGD tips and tricks | |
Tues, Feb 7 | Training Neural Nets II: overfitting, parameter updates, ensembles, plus Practical Intro to Caffe | slides, Neural Net Notes 2 and 3 | |
Thurs, Feb 9 | Snow Day | ||
Tues, Feb 14 | Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift Sergey Ioffe, Christian Szegedy, arXiv, 2015. | slides,arXiv | Amit and Sambit |
Thurs, Feb 16 | Intro to Convolutional Neural Networks, Spatial Localization and Detection | slides | |
Tues, Feb 21 | ImageNet Classification with Deep Convolutional Neural Networks. Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton. NIPS 2012. | pdf, slides | Lisa and Jason Krone |
Thurs, Feb 23 | Last Day to Drop | ||
Thurs, Feb 23 | Presidents' Day (Observed) | ||
Friday, Feb 24 | Assignment #2 Due | ||
Tues, Feb 28 | Vizualizing CNNs and Recurrent Neural Nets, Long Short Term Memory | slides | |
Thurs, Mar 2 | Final Project Proposals Due | proposal requirements, Stanford cs231n recommendations on DL Libraries | |
Thurs, Mar 2 | Training CNNs in practice, plus Practical Intro to TensorFlow | slides,Stanford course on TensorFlow | |
Tues, Mar 7 | You Only Look Once: Unified, Real-Time Object Detection Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi. arXiv 2016. | slides, arXiv, project page | Takuto and Jie |
Thurs, Mar 9 | Assignment #3 Due | ||
Thurs, Mar 9 | SSD: Single shot multibox detector. Liu, Wei, et al. ECCV 2016. | slides, paper | Nathan and Hongyan |
Tues, Mar 14 | Fully Convolutional Networks for Semantic Segmentation. Jonathan Long, Evan Shelhamer, Trevor Darrell. CVPR 2015. | arXiv | Jay and Jason Fan -- RESCHEDULED for snow |
Thurs, Mar 16 | Deep Visual-Semantic Alignments for Generating Image Descriptions. Andrej Karpathy and Li Fei-Fei. CVPR 2015. | slides, paper | Jonathan and Justin |
Tues, Mar 21 | Spring Break | ||
Thurs, Mar 23 | Spring Break | ||
Tues, Mar 28 | Understanding Deep Image Representations by Inverting Them. Aravindh Mahendran, Andrea Vedaldi. CVPR 2015. | arXiv, slides | Xinmeng and Beibei |
Tues, Mar 28 | Fully Convolutional Networks for Semantic Segmentation. Jonathan Long, Evan Shelhamer, Trevor Darrell. CVPR 2015. | arXiv, slides, demo notebook | Jay and Jason Fan |
Thurs, Mar 30 | Assignment #4 Due | ||
Thurs, Mar 30 | Segmentation and Pose Estimation | slides | |
Tues, Apr 4 | Final Project Milestone Due | milestone requirements | |
Tues, Apr 4 | Activity Recognition and Unsupervised Learning | slides | |
Thurs, Apr 6 | Special Guest: Bolei Zhou | slides | |
Tues, Apr 11 | Using very deep autoencoders for content-based image retrieval. Krizhevsky, Alex, and Geoffrey E. Hinton. ESANN. 2011. | pdf, slides | Chris and Ben |
Thurs, Apr 13 | Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. Alec Radford, Luke Metz, Soumith Chintala. 2015. | slides, project page, arXiv | Jorge |
Tues, Apr 18 | Hierarchical Question-Image Co-Attention for Visual Question Answering Jiasen Lu, Jianwei Yang, Dhruv Batra , Devi Parikh, NIPS 2016. | slides, arXiv | Hossein and Dylan |
Thurs, Apr 20 | Update - Paper Changed to: Image-to-Image Translation with Conditional Adversarial Networks Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros |
Update: slides, arXiv |
Alex and Sam Burck |
Tues, Apr 25 | Learning to Generate Chairs, Tables and Cars with Convolutional Networks. Alexey Dosovitskiy, Jost Tobias Springenberg, Maxim Tatarchenko, Thomas Brox. CVPR 2015. | slides, arXiv | Cole and Sam Woolf |
Thurs, Apr 27 | Attention Mechanism and Residual Networks | slides | |
Friday, May 12 12pm - 3pm, Microsoft New England Research and Development (NERD), 1 Memorial Drive 1st Floor, Cambridge, MA. Adams/Attucks Conference Room. | Final Project Presentations * Note: Final Project reports due 11:59 PM EST on day of Final Exam. * | Everybody (20 min presentation time per group including questions. This is a hard limit, presentations will be cut off at 20 mins.) |