Blogs
1. Handwritten Digits Classification (Python)
Github
- The Handwritten Digits Classification project aims to classify images of handwritten digits from 0 to 9 using neural networks.
- The code uses TensorFlow and Keras to create a simple neural network with an input layer of 784 elements and an output layer of 10 elements.
- The input images are flattened into a single column containing 784 elements to be fed as input to the neural network.
- The model is trained on the MNIST dataset with 60,000 images of 28x28 pixels for five epochs and achieves an accuracy of 92.55%.
- Finally, the model is evaluated on the test dataset with 10,000 images and achieves an accuracy of 97.73%.
2. Home Price Deduction
Github
- This Python code utilizes pandas, numpy, and scikit-learn to perform linear regression for predicting home prices based on their areas. It trains a model on the data from
homeprices.csv
, visualizes it, and predicts prices for new areas from areas.csv
.
3. Canada per-capita-income
Github
- Conducted linear regression analysis on Canada’s per capita income data from 1970 to 2017 using pandas, numpy, and sklearn libraries.
- Predicted per capita income for the year 2020 using the linear regression model and manually calculated the same using the formula
y = mx + b
.Visualized the data and model predictions using matplotlib.