Changes between Version 1 and Version 2 of Other/Summer/2024/ml5G


Ignore:
Timestamp:
Jun 12, 2024, 4:41:11 PM (5 weeks ago)
Author:
aadhil621
Comment:

—

Legend:

Unmodified
Added
Removed
Modified

  • Other/Summer/2024/ml5G

    v1 v2  
    11
    2 == **Week 1 (5/28 - 5/30)**
     2**Week 1 (5/28 - 5/30)**
    33
    4 We installed and familiarized ourselves with GNU Radio.
    5 We also explored the architecture of the Orbit test bed.
    6 Reviewed several papers to gain insights into the current scenario of 5G networks and the interference mitigation techniques used across different frequency ranges.
     4We installed and familiarized ourselves with GNU Radio. \\
     5
     6We also explored the architecture of the Orbit test bed. \\
     7
     8Reviewed several papers to gain insights into the current scenario of 5G networks and the interference mitigation techniques used across different frequency ranges.\\
    79
    810
    9 == **Week 2 (6/03 - 6/06)**
    1011
    11 We delved into the context of HyPhyLearn and conducted an in-depth exploration of Domain Adversarial Neural Networks (DANN).
    12 Ran reference code for DANN and examined the source, target, and domain accuracies.
    13 Analyzed graphs that demonstrated the model's ability to learn from domain-invariant features.
     12**Week 2 (6/03 - 6/06)**
     13
     14We delved into the context of HyPhyLearn and conducted an in-depth exploration of Domain Adversarial Neural Networks (DANN). \\
     15
     16Ran reference code for DANN and examined the source, target, and domain accuracies. \\
     17
     18Analyzed graphs that demonstrated the model's ability to learn from domain-invariant features.\\
    1419
    1520
    16 == **Week 3 (6/03 - 6/06)**
    1721
    18 We explored the TensorFlow code of the HyPhyLearn model, which classifies 2D Gaussian datasets.
    19 Augmented the code from TensorFlow 1.0 to PyTorch and validated the experimentation.
    20 Additionally, we conducted research on works with similar use cases and reviewed research papers to gain proper knowledge on setting up a physical model for generating synthetic data.
     22**Week 3 (6/03 - 6/06)**
     23
     24We explored the TensorFlow code of the HyPhyLearn model, which classifies 2D Gaussian datasets. \\
     25
     26Augmented the code from TensorFlow 1.0 to PyTorch and validated the experimentation. \\
     27
     28Additionally, we conducted research on works with similar use cases and reviewed research papers to gain proper knowledge on setting up a physical model for generating synthetic data.\\