Biscuits of Deep Learning
Manipulate Gradient The section includes some technologies related to gradient descent optimization method. Gradient Clipping A good explanation: What is Gradient Clipping? Related paper: Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity (ICLR'2020) Sometimes the training loss may not stable, it may caused by exploding problem. A simple…
[Revised] Basic Theory of Covolutional Neural Network
Outline In this presentation, we present the DNN and CNN structure We briefly shows some famous CNN works (structure, improvements, performance) Difficulty of training DNN and shows a good solution (ResNet) Revised Version [2021-06-25] A revised version can be download from Download_Link Slides [embeddoc url="" download="all" viewer="microsoft"]
[Revised] Basic Theory of Neural Network
Content In the document, we present: Each neural network (NN) consists of many neurons, and each neuron has two elements: linear function and activation function. We have shown the reason of using activation functions. (choices of activation functions) Two numerical examples have been given to track the forward and backward…
Neural Style Transfer via Meta Networks
Outline Introduction Style transfer Content-perceptual loss Style-perceptual loss Example Proposed Method (simple but inspirational) Arbitrary style transfer Meta networks for arbitrary style transfer Experiments Conclusion Slides [pdf-embedder url="" title="20200116_Meta Network for Neural Style Transfer"]
Experiment Control
Prepare the environment of the experiment control Tutorial from Installation To install Sacred at client (t.g. conda environment) pip install sacred pip install numpy pymongo Server: database # 1. Import the public key used by the package management system. wget -qO - | sudo apt-key add - #…
Useful tools
Auto notification of modification of a web page Select an area and relax: It will send an email alert when something changes. Just from:
Sentences in Paper Writing
Feature Vocabulary: boost the representation power A Feature aggregation strategy is proposed to propagate information from early stags to the later ones. -- (Li, et al. 2019) “Retinking on Multi-Stage Networks for Huma Pose Estimation” A multi-stage network is vulnerable by the information losing during repeated up and down sampling.…
Article Writing
Phrasebank Proof Reading Paraphrasing
A Image Quality Evaluation Toolbox For MATLIB
MeTriX MuX Visual Quality Assessment Package The name of the package is MeTriX MuX Visual Quality Assessment Package. The official website does not work (attempt on 08-Sep-2019), and the download link is invaild. I find a copy that is from a github repository Installation It can be easily…