Yang's research group wiki

User Tools

Site Tools

Trace:
trans_learn:2021projects

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
trans_learn:2021projects [2021/10/14 08:22] – [Meeting Notes] hanbingtrans_learn:2021projects [2022/01/05 21:59] (current) – yang
Line 1: Line 1:
 ====== 2021 Project Page ====== ====== 2021 Project Page ======
 +===== Transfer learning for battery parameter estimation =====
 ==== Meeting Notes ==== ==== Meeting Notes ====
  
Line 10: Line 10:
           * research: optimal transport and domain adaptation problem           * research: optimal transport and domain adaptation problem
           * reading: Joint distribution optimal transportation for domain adaptation; Few-Shot Cross Domain Battery Capacity Estimation           * reading: Joint distribution optimal transportation for domain adaptation; Few-Shot Cross Domain Battery Capacity Estimation
-          * +          * slides: {{ :trans_learn:optimal_transport_and_domain_adaptation.pptx |optimal transport and domain adaptation}}
      
   * TODO:    * TODO: 
Line 27: Line 27:
           * reading: Adversarial Discriminative Domain Adaptation           * reading: Adversarial Discriminative Domain Adaptation
           * research: Adversarial network in Domain Adaptation           * research: Adversarial network in Domain Adaptation
 +          * slides: {{ :trans_learn:adversarial_domain_adaptation.pptx |adversarial domain adaptation}}
   * TODO:   * TODO:
         * Yanru:          * Yanru: 
Line 37: Line 38:
           * deeper reading ADDA to find its advantage over other adversarial domain adaptation works           * deeper reading ADDA to find its advantage over other adversarial domain adaptation works
           * modify the ADDA model to deal with battery features           * modify the ADDA model to deal with battery features
 +
 +== 2021/10/20 ==
 +
 +  * Attendee: Hanbing, Yanru, Yang
 +  * Meeting summary:
 +        * Yanru: 
 +          * experiment: H-score trial on task transfer using ADE20K  -- especially good results for 'sky' task
 +        * Hanbing:
 +          * experiment: ADDA using battery pulse data 
 +          * slides:{{ :trans_learn:adda_test.pptx |}}
 +  * TODO:
 +        * Yanru:
 +          * recode the experiment with pytorch
 +          * cityscape dataset preprocessing
 +          * change of target data size
 +          * reading
 +        * Hanbing:
 +          * change convolution layer to fully connect or conv1D
 +          * transform battery data into frequency domain
 +
 +== 2021/11/10 ==
 +
 +  * Attendee: Hanbing, Yang
 +  * Meeting summary:
 +    * Hanbing:
 +      * experiment: unsupervised fully connection ADDA using battery pulse data
 +  * TODO:
 +    * Hanbing:
 +      * experiment:
 +        - source only: divide source dataset into training set and testing set to see if model is overfitting
 +        - target only: using only target data to get target baseline model
 +        - transfer learning: finetuning target feature extractor and source classifier useing a few target label
 +
 +== 2021/11/14 ==
 +  * Attendee: Yanru, Yang
 +  * Meeting summary:
 +    - A brief review of several papers related to spatial-temporal data analyses ({{ :trans_learn:project_reading.pdf |}})
 +    - Notes: {{:trans_learn:notes1114.png?linkonly|}}
 +  * TODO: write background part of project plan 
 +
 +== 2021/11/17 ==
 +  * Attendee: Hanbing, Yang
 +  * Meeting summary:
 +    * Hanbing:
 +      * experiment:
 +        - source only and target only on original net and simplified net  
 +        - add penalty term on target model
 +  * TODO:
 +    * Hanbing:
 +      * experiment:
 +        - finetunning target model useing a few target label
 +        - change visual form of result 
trans_learn/2021projects.1634214163.txt.gz · Last modified: 2021/10/14 08:22 by hanbing