Machine-Learning-and-Deep-Learning

🚀 Exploring Machine Learning & Deep Learning | Personal and Guided Projects

Welcome to my Machine Learning Repo! I'm passionate about diving deep into the world of machine learning (ML) and deep learning (DL). Here, you'll find a collection of my personal and guided projects where I experiment with various ML/DL algorithms and techniques to enhance my skills.

1. Image Segmentation with Pytorch. Used Unet Architecture to get the segmentaiton of the image. For this instance, took segmentation of human. Trained on a dataset consisting of human.
   • Skills : Convolutional Neural Network, Autoencoder, Python Programming, PyTorch.
2. Deep Learning with PyTorch : Siamese Network. Trained a network using Triplet loss function. Create Anchor, Positive, Negative image datase, which was used as input to the triplet loss function.
   • Applications : Face Recognition, Signature Checking, Person re-identification, etc.
   • Skills : Pytorch, Triplet Loss function, State of the Art architecture - efficientnet_b0
3. Deep Learning with PyTorch : Facial Expression Recognition. Load pretrained SOTA model to train on facial expression dataset. Classify on the basis of expression into 7 different classes.
   • Skills : Convolutional Neural Nework, Classifier
4. Naive Bayes Classifier
5. Linear Regression
   • Multiple Linear Regression
   • Multicollinearity Linear Regression
6. SVM (Support Vector Machine)
7. K-Means Clustering
   • Using clustering class and kmeans class implemented K-means clustering algorithm
   • Usage of dataclass for Clustering : locations (centroid), vectors
   • matplotlib scatter plot to visualize all the data points with 5 centroids.