Please check my notes for Transfer Learning introduction! Transfer Learning
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 »
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 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 »
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 »
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 »
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 »