Hardik Asnani's repositories
sentiment-analysis-leveraging-lstm
I built Sentiment Analysis models leveraging a deep learning approach utilizing the customer reviews of Amazon products. Since Long Short Term Memory Network (LSTM) is very effective in dealing with long sequence data and learning long-term dependencies, I used it for automatic sentiment classification of future product reviews.
diamond-price-and-carat-prediction
I leveraged an algorithmic approach to predict the price and carat of the diamond using Machine Learning. Various regression models have been trained and their performance has been evaluated using the R Squared Score followed by tuning of the hyperparameters of top models. I have also carried out a trade-off based on the R Squared Score and the Run-Time to take a situational decision to select the best model.
dimensionality-reduction-on-microbiome-dataset
I performed PCA and t-SNE on the microbiome dataset and visualized the data in 2D space. I also report what I learned from the PCA and t-SNE analyses.
gpt3-language-model
Presentation and Practical on a popular NLP paper - Language Models are Few-Shot Learners.
classifying-and-clustering-the-newsgroups
I leveraged an algorithmic approach for document classification and document clustering. Various models have been trained for document classification and they all have been evaluated using performance metrics followed by tuning of the model hyper-parameters to reach the most accurate classification. Additionally, a model has been trained for document clustering, which is followed by a dimensionality reduction technique to visualize the document clusters in 2D space.
ensemble-methods-on-breast-cancer-data
I applied the bagging and boosting methods using the decision tree as the base predictor on the sklearn’s breast cancer data set. I experiment with different parameters and report the results obtained.
handwritten-digit-recognition-system
I implemented a CNN to train and test a handwritten digit recognition system using the MNIST dataset. I also read the paper “Backpropagation Applied to Handwritten Zip Code Recognition” by LeCun et al. 1989 for more details, but my architecture does not mirror everything mentioned in the paper. I also carried out a few experiments such as adding different dropout rates, using batch normalization, and using different optimizers in the baseline model. Finally, I discuss the impact of experiments on the learning curves and testing performance.