Difference between revisions of "User:Skohli"

From REU@MU
Jump to: navigation, search
(→‎Milestones)
(→‎Weekly Log)
 
(22 intermediate revisions by the same user not shown)
Line 1: Line 1:
 
==Personal Information==
 
==Personal Information==
−
* Incoming junior | Computer Science major at Marquette
+
* Incoming junior | Computer science major at Marquette
  
 
* Working with Dr. Povinelli in the GasDay Lab
 
* Working with Dr. Povinelli in the GasDay Lab
−
 
−
== Milestones ==
 
−
'''Week 0'''
 
−
*Read Literature
 
−
'''Week 1'''
 
−
*Read literature related to the topic.
 
−
'''Week 2'''
 
−
* DON'T GIVE UP
 
−
'''Week 3'''
 
−
*Gather Data
 
−
'''Week 4'''
 
−
*Learn Caffe (?)
 
−
'''Week 5'''
 
−
* Have preliminary models
 
−
* REU presentation
 
−
'''Week 6'''
 
−
*GasDay presentation
 
−
* Draft Paper
 
−
'''Week 7'''
 
−
* Second round of models
 
−
'''Week 8'''
 
−
*Deal with errors
 
−
* GasDay presentation
 
−
'''Week 9'''
 
−
*Finish with papers and presentations
 
−
[[File:IMG_3570.jpg]]
 
  
 
== Weekly Log==
 
== Weekly Log==
Line 38: Line 12:
 
*Read Bengio Learning Deep Architectures for AI
 
*Read Bengio Learning Deep Architectures for AI
 
*Found more material to read.
 
*Found more material to read.
 +
* Attended weekly book club meeting as suggested by mentor
 +
* Read chapter 1-3 in the book titled Deep Learning Book
 +
* Read Probabilistic Forecasting by Gneting and Katzfuss
 +
*Additive models and robust aggregation for GEFcomp2014 probabilistic electric load and electricity price forecasting by Gaillard, Goude, Nedellec.
 +
*Read DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
 +
*Met Dr. Povinelli 4 times: to discuss possible project topics, to get oriented with the lab, to decide on a project topic, and to establish weekly milestones
 +
'''Week 2 (June 5 - June 9)'''
 +
*Read chapter 4 of deep neural network book
 +
*Attended GasDay camp
 +
** Learned what GasDay does
 +
** Benefits of working at GasDay
 +
** Further research opportunities at GasDay
 +
** How to work in a team
 +
* Attended the Ethical research training
 +
** Learned key concepts such as not fabricating, falsifying, and plagiarizing
 +
*Read
 +
**10.1109/PMAPS.2016.7764155
 +
**https://doi.org/10.1016/j.energy.2016.07.090
 +
**http://www.sciencedirect.com/science/article/pii/S1568494617302946
 +
*Met Dr. Povinelli 3 times to discuss current progress
 +
* Attended weekly book club meeting as suggested by mentor
 +
'''Week 3 (June 12 - June 16)'''
 +
*Tasks undertaken to improve skills
 +
**Completed 6 weeks of the coursera tutorial on Machine Learning
 +
**Completed 6 weeks of the Stanford class on Convolution Neural Networks for Visual Recognition
 +
**Learned basics of Python
 +
*Completed portion of online RCR training
 +
* Attended weekly book club meeting as suggested by mentor
 +
*Met Dr. Povinelli 2 times to discuss current progress
 +
*Collected data
 +
'''Week 4 (June 19 - June 23)'''
 +
*Go through Machine Learning tutorials online
 +
*Try to learn tensorflow
 +
*Try to learn Quantile regression
 +
*Understand Pinball Loss Function
 +
'''Week 5(June 26 - June 30)'''
 +
*Prepare slides for presentation
 +
*Present presentation
 +
*Work with Keras
 +
*Make prelimary models
 +
*Wish for faster computers
 +
*Implement the pinball loss function with different methods:
 +
**Convolutional neural networks
 +
**ResNets
 +
**Feed Forward
 +
***Keras api for models
 +
*** WIthout Keras api for models
 +
*Implement the Winkler Score
 +
*Read Attention is all you need
 +
'''Week 6 (July 3 - July 6)'''
 +
*https://arxiv.org/pdf/1706.02515.pdf
 +
*Tried different deep learning techniques
 +
**CNN
 +
**ResNet
 +
**RNNS
 +
**Feed forward
 +
***Hyperamaters
 +
*Presented at GasDay
 +
*Attended how to make a good poster presentation
 +
'''Week 7 (July 8 - July 15)'''
 +
*Adapted the technique from DeepAR
 +
*Tried different methods surrounding it
 +
*Choose which method I will stick with
 +
'''Week 8(July 17- July 21)'''
 +
*Spent week trying to see why val and test scores are extremely different
 +
*Ran models with different data sets to see why that is happening
 +
'''Week 9(July 24 - July 28)'''
 +
*Finishing up poster
 +
*Finishing up presentation
 +
*Starting to write paper
 +
*Cleaning code
 +
*Present at GasDay
 +
*Make changes to model
 +
*Run final models
 +
'''Week 10(July 31 - August4)'''
 +
*Prepared for poster session
 +
*Prepared final presentation
 +
*Finished paper

Latest revision as of 15:23, 2 August 2017

Personal Information

  • Incoming junior | Computer science major at Marquette
  • Working with Dr. Povinelli in the GasDay Lab

Weekly Log

Week 1 (May 30 - June 2)

  • Discussed preliminary project ideas with other researchers and mentor.
  • Attended library tour.
  • Attended the talk on how to conduct research.
  • Read paper on the GEFcomp2014- Hongetal2016
  • Read Bengio Learning Deep Architectures for AI
  • Found more material to read.
  • Attended weekly book club meeting as suggested by mentor
  • Read chapter 1-3 in the book titled Deep Learning Book
  • Read Probabilistic Forecasting by Gneting and Katzfuss
  • Additive models and robust aggregation for GEFcomp2014 probabilistic electric load and electricity price forecasting by Gaillard, Goude, Nedellec.
  • Read DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
  • Met Dr. Povinelli 4 times: to discuss possible project topics, to get oriented with the lab, to decide on a project topic, and to establish weekly milestones

Week 2 (June 5 - June 9)

  • Read chapter 4 of deep neural network book
  • Attended GasDay camp
    • Learned what GasDay does
    • Benefits of working at GasDay
    • Further research opportunities at GasDay
    • How to work in a team
  • Attended the Ethical research training
    • Learned key concepts such as not fabricating, falsifying, and plagiarizing
  • Read
  • Met Dr. Povinelli 3 times to discuss current progress
  • Attended weekly book club meeting as suggested by mentor

Week 3 (June 12 - June 16)

  • Tasks undertaken to improve skills
    • Completed 6 weeks of the coursera tutorial on Machine Learning
    • Completed 6 weeks of the Stanford class on Convolution Neural Networks for Visual Recognition
    • Learned basics of Python
  • Completed portion of online RCR training
  • Attended weekly book club meeting as suggested by mentor
  • Met Dr. Povinelli 2 times to discuss current progress
  • Collected data

Week 4 (June 19 - June 23)

  • Go through Machine Learning tutorials online
  • Try to learn tensorflow
  • Try to learn Quantile regression
  • Understand Pinball Loss Function

Week 5(June 26 - June 30)

  • Prepare slides for presentation
  • Present presentation
  • Work with Keras
  • Make prelimary models
  • Wish for faster computers
  • Implement the pinball loss function with different methods:
    • Convolutional neural networks
    • ResNets
    • Feed Forward
      • Keras api for models
      • WIthout Keras api for models
  • Implement the Winkler Score
  • Read Attention is all you need

Week 6 (July 3 - July 6)

  • https://arxiv.org/pdf/1706.02515.pdf
  • Tried different deep learning techniques
    • CNN
    • ResNet
    • RNNS
    • Feed forward
      • Hyperamaters
  • Presented at GasDay
  • Attended how to make a good poster presentation

Week 7 (July 8 - July 15)

  • Adapted the technique from DeepAR
  • Tried different methods surrounding it
  • Choose which method I will stick with

Week 8(July 17- July 21)

  • Spent week trying to see why val and test scores are extremely different
  • Ran models with different data sets to see why that is happening

Week 9(July 24 - July 28)

  • Finishing up poster
  • Finishing up presentation
  • Starting to write paper
  • Cleaning code
  • Present at GasDay
  • Make changes to model
  • Run final models

Week 10(July 31 - August4)

  • Prepared for poster session
  • Prepared final presentation
  • Finished paper
Retrieved from "https://reu.cs.mu.edu/index.php?title=User:Skohli&oldid=2761"