SJP SCI-TECH CLUB
  • Home
  • Student Research
    • Eel Grass Studies
    • Aquaponics Blog
    • Wind Energy Research
    • Deep Learning for BCI
    • Cloud Chamber Blog
    • And much more.. >
      • Bioluminesence
  • Lab Visits
    • Novartis Cambridge
    • Greentown Labs
    • MASS CEC
    • MIT Plasma Physics Center
    • Histogenics
    • US GreenBuild - Boston
  • Physics Olympics
    • Paper Airplanes
    • Glider Competition
  • Internships + More
    • Histogenics 2017
Picture

Result and Conclusion

4/23/2018

 

Test Accuracy for the AE-LSTM-FFN Algorithm

Picture

Test Accuracy for the Support Vector Machine algorithm

Picture
The best version of my algorithm achieves about 75% accuracy. The classical Support Vector Machine algorithm (SVM), however, has only 70% accuracy in average. In addition to the accuracy that my algorithm can achieve, it also has smaller variance, compared to the SVM. SVM algorithm has a variance around 20% in average, but my algorithm has only 5% variance due to the effectiveness of the autoencoder. In conclusion, the deep learning algorithm does outperform the classical algorithm. 

Comments are closed.

    Author

    Jack Lin 

    Archives

    April 2018
    March 2018

    Categories

    All

    RSS Feed

Proudly powered by Weebly
  • Home
  • Student Research
    • Eel Grass Studies
    • Aquaponics Blog
    • Wind Energy Research
    • Deep Learning for BCI
    • Cloud Chamber Blog
    • And much more.. >
      • Bioluminesence
  • Lab Visits
    • Novartis Cambridge
    • Greentown Labs
    • MASS CEC
    • MIT Plasma Physics Center
    • Histogenics
    • US GreenBuild - Boston
  • Physics Olympics
    • Paper Airplanes
    • Glider Competition
  • Internships + More
    • Histogenics 2017