This repository contains my code and projects from the FruitPunch AI in Practice BootCamp (Online), which I started in March 2023 and finished in April 2023. In this bootcamp, I have gained practical experience in several machine learning techniques using various datasets. Below is a brief summary of my experience so far:
Files:
- CNN_fashion_mnist.py:
- Optimized a convolutional neural network using dropout and batch normalization to achieve 98% accuracy for the model when trained on the fashion mnist data set.
- CNN_mnist.py: Developed a convolutional neural network to train and predict items from the mnist data set
- ML_Models.py: Practiced using various machine learning techniques to evaluate different data sets from the scikit-learn library
- NN_From_Scratch.py: Built a Neural Network from scratch using scikit-learn and keras from the tensorflow library to add layers and optimize the models Mean Squared Error value until it got around 15.0
- XGBoost.py: Evaluates the same data sets as the ML_Models python file only this time using the XGBRegressor() class from the xgboost library
Conclusion: Overall, the FruitPunch AI in Practice BootCamp (Online) has provided me with valuable hands-on experience in machine learning techniques, which I look forward to applying to future projects. If you have any questions or would like to learn more about my experience, please feel free to reach out.