From Stanford University's Deep Learning course (CS230):
Course Description Deep Learning is one of the most highly sought after skills in AI. We will help you become good at Deep Learning. In this course, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow, which we will teach. After this course, you will likely find creative ways to apply it to your work. This class is taught in the flipped-classroom format. You will watch videos and complete in-depth programming assignments and online quizzes at home, then come to class for advanced discussions and work on projects. This class will culminate in an open-ended final project, which the teaching team will help you on.
Final Project Prize Winners
- First place: Image-to-Image Translation with Conditional-GAN (Weini Yu, Jason Hu, Yujo Zhouchangwan Yu)
- Second place: Deep Knowledge tracing and Engagement with MOOCs (Klint Kanopka, Kritphong Mongkhonvanit, David Lang)
- Third place: Deep Learning for Improving Power-Accuracy of Heart Rate Monitors (Albert Gural)
Outstanding Posters
- First place: Painting Outside the Box: Image Outpainting with GANs (Mark Sabini, Gili Rusak)
- Second place: LeafNet: A Deep Learning Solution to Tree Species Identification (Krishna Rao, Elena Herrero, Gabrielle Pacalin)
- Third place: Earthquake warning system: Detecting earthquake precursor signals using deep neural networks (Mustafa Al Ibrahim, Jihoon Park, Noah Athens)
Submissions
- LSTM Music Generation by Xingxing Yang: report poster
- Extracting High-Quality Poster Images From Videos by Katie Fo, Nat William Gardenswartz, Tam N Dinh: report poster
- Image Colorization by Alex Avery, Dhruv Amin: report poster
- Sketch Classification by Sushan Bhattarai: report poster
- DeepSecurity Cybersecurity Threat Behavior Classification by Giovanni Sean Paul Malloy, Isaac Justin Faber, Isha Thapa: report poster
- Predicting the Success of Crowdfunding by Chenchen Pan, Yan Chen, Yiwen Guo: report poster
- Classification of blood cell subtypes by Sharon Shin Newman, Therese Maria Persson: report poster
- Simulating nanophotonic neural networks at a component level by Ben Bartlett: report poster
- Image Restoration of Low-Quality Medical-Diagnostic Images by Fariah Hayee, Katherine Lee Sytwu: report poster
- Automatic Chord Arrangement from Melodies by Shuxin Meng, Yulou Zhou: report poster
- Project Sunroof by Pranjal Patil, Vedang Hemant Vadalkar: report poster
- Brain Computer Interface: Using Neural Activity to Predict Cursor Kinematics by Jonathan Henry Zwiebel, Robert Terrell Ross, Samuel Lurye: report poster
- Guaging Political Bias on Twitter by Catherine Frances Lee, Jacob Shiff, Sridatta Thatipamala: report poster
- DeepFugue: a model to generate Baroquestyle fugues by Aditya Chander, Samantha Elinon Silverstein, Marina Barbara Cottrell: report poster
- Deep Learning for Partial Differential Equations (PDEs) by Bella Shi, Kailai Xu, Shuyi Yin: report poster
- ChexNet2: Improvements for The Detection of Pneumonia with Deep Learning by Alexander Kucy, Liam Hassen Neath: report poster
- Neural Network based Building Earthquake Vulnerability Prediction by Haiwen Wang, Zhaozhuo Xu, Zhiyuan Li: report poster
- Image Super-Resolution for Facial Recognition by Corey Tze-chung Shih: report poster
- Neural Networks for Baseball Data Analysis by Yifan Pi: report poster
The kids are alright.
