In this project, we are introduced to exploratory data analysis using some of the Python data science libraries such as pandas, NumPy, and matplotlib in Jupyter Notebook, and try to solve this problem.
In this project, a problem is solved using various searching methods including BFS, IDS, and weighted A*.
The problem is searching a graph for recipes, and giving them to the ones who need them in minimum time.
In this project, An investment problem is solved using a genetic algorithm. We find share that we buy from each to get a good return with low risk.
In this project, Othello is played by two agents. One of them uses the alpha-beta minimax algorithm to play optimally, while the other agent plays randomly.
In this project, the class of a numbers is predicted using an implementation of the Naïve Bayes classifier. We used methods like Gaussian Naïve Bayes and Bernoulli Naïve Bayes and techniques like Additive smoothing.
In this project, different classifiers are trained on a dataset and the models are tested.
A home price dataset is preprocessed, split, and used to train a Linear Regression, Decision Tree, K-Nearest Neighbors, Logistic Regression, and Random Forest model to predict price of a house with given features.
- Phase 1:
In this project, a neural network is implemented and trained to classify different datasets like sklearn.datasets.make_moons, sklearn.datasets.make_circles, sklearn.datasets.make_classification.
Then we trained a model on people reviews on imdb and used PyTorch to train a model. The feedforward neural network and various activation functions are implemented and the effects of different parameters are checked. - Phase 2: Keras and TensorFlow library are used to classify the CIFAR-10 dataset. different methods like Data Augmentation or Regularization are used to improve performance of our model.