Learnt about Basic Python Commands, Data structures, Variables, NumPy, Pandas, Matplotlib and Seaborn, and Sci-Kit Learn, and how to conduct Exploratory Data Analysis (EDA). Learnt how to utilize Python to conduct Machine Learning Simple Regression, Polynomial Regression & Model Tuning. Learnt how to perform One-Hot Encoding, how to graph Scatter Plots.

Determined how to use the concept of Multiple Regression, the concept of underfitting, overfitting, dangers of false positives and false negatives, backpropagation of neural networks. Learnt how to do Logistic Regression in examples such as Accurate diagnosis of breast cancer, and how to Adjust the threshold. Understood about the basic pipeline of fitting a simple neural network model with a Train-Test Split and using Deep Learning to reduce the mean squared error of the data even further.Understood the importance of Validation Sets while tuning neural networks.

Learnt how to tune Neural Networks and use it for image recognition for Classification. Was introduced to create, build, train Convolution Neural Networks (CNN) and understand how to improve the CNN model after viewing examples of incorrectly classified test data. Understood using the average pooling, max pooling, dropout, strides, padding, and Convolution function to prevent CNN models from overfitting while making predictions on a dataset.

Learnt how to perform Transfer Learning to speed up computation.