Please check my notes for Transfer Learning introduction! Transfer Learning
Slideshare (4): A brief Introduction on Transfer Learning
Posted by in SlideShare, Theory Author: Irene
Keep calm and update blog.
Posted by in SlideShare, Theory Transfer Learning Materials
Posted by in Theory Keep Updating…. Thesis: Deep Learning Models for Unsupervised and Transfer Learning PhD Thesis, University of Toronto, May 2017 Transfer Learning Techniques for Deep Neural Nets , Steven Michael Gutstein, 2010 Feature-based Transfer Learning and Real-world applications, Sinno Jialin Pan Survey: http://www.jmlr.org/papers/volume10/taylor09a/taylor09a.pdf (with Reinforcement Learning 2009) https://www.cse.ust.hk/~qyang/Docs/2009/tkde_transfer_learning.pdf (2009) ijcai13.org/files/tutorial_slides/td2.pdf (applications) https://arxiv.org/pdf/1705.04396.pdf (2017) https://arxiv.org/pdf/1707.08114.pdf (2017) (Multi-task Learning)…Read more »
Slideshare (3): Unsupervised Transfer Learning Methods
Posted by in Deep Learning, SlideShare, Theory A brief introduction on unsupervised transfer learning methods. The presentation focused on unsupervised transfer learning methods, introducing feature-based and model-based strategies and few recent papers from ICML, ACL. Unsupervised Transfer Learning Comments are welcomed!
TensorFlow 08: save and restore a subset of variables
TensorFlow provides save and restore functions for us to save and re-use the model parameters. If you have a trained VGG model, for example, it will be helpful for you to restore the first few layers then apply them in your own networks. This may raise a problem, how do we restore a subset of…Read more »
To copy or not, that is the question: copying mechanism
Posted by in Deep Learning, Theory In our daily life, we always repeating something mentioned before in our dialogue, like the name of people or organizations. “Hi, my name is Pikachu”, “Hi, Pikachu,…” There is a high probability that the word “Pikachu” will not be in the vocabulary extracted from the training data. So in the paper (Incorporating Copying Mechanism in…Read more »
What matters: attention mechanism
Posted by in Theory People would be attracted only on a part of an image, say a person on a photo. Similarly, for a given sequence of words, we should pay attention to few keywords instead of treating each word equally. For example, “this is an apple”, when you read it loudly, I am sure you will stress “apple”…Read more »
What’s next: seq2seq models
Posted by in Theory The short blog contains my notes from Seq2seq Tutorial. Please leave comments if you are interested in this topic. Seq2seq model is a typical model which takes sequences as inputs and another sequence as the outputs. What are sequences? Think about an article as a sequence of words or a video file as a sequence…Read more »
