Built a model to predict future Avocado market prices, using FbProphet

Built an optimal model to estimate the best-selling prices for clients homes. Used statistical analysis procedures and machine learning algorithms on Boston Housing data to develop this method. User can use this model to predict the selling prices of houses.

· Applied an LSTM to music generation

· Generate your own jazz music with Deep Learning

· Stored text data for processing

· Synthesized data, by sampling predictions at each time step and passing it to the next RNN-Cell Unit

- Built a character-level text generation recurrent neural network

· Implemented a model which inputs a sentence (such as "Let's go see the baseball game tonight!") and finds the most appropriate emoji to beused with this sentence (⚾️)

· Implemented a 2-class classification neural network with a single hidden layer

· Used units with a non-linear activation function, such as tanh

· Computed the cross-entropy loss

· Implemented forward and backward propagatio

Built an LSTM Bidirectional model using tensor flow backend to translate from one language to another, such as translating from English to French

· Built the general architecture of an Artificial Neural Networks algorithm.

• Initialized parameters
• Calculated the cost function and its gradient

Used an optimization algorithm (gradient descent)

· Trained an ANN such as a Convolutional Neural Network(CNN) to recongnize 105 different flower species

• Load and preprocess the image dataset
• Train the image classifier on your dataset

Use the trained classifier to predict image content

· Equipped the distributor with insight into how to best structure their delivery service to meet the needs of each customer

· Displayed a description of the dataset, visualized the amount of each product purchased for each sample with the dataset mean, predict the cluster for each transformed sample data point.

Distributor can use this system to predict which type of delivery system is best for a given customer

· Self-driving agent to learn to drive on the city roads while obeying traffic rules, avoiding accidents, and reaching passengers’ destinations in the allotted time.

· Coded the agent module to explore its environment through reward system in a table that the Smart cab could use to successfully move around the city

Used Le-Net Architecture Network from Keras to build a smart model capable of classifying Traffic signs

Built a model smart enough to distinguish spams from email messages using Naïve Bayes MultinominalNB

Built a model that can recommend movies one may like based on the movies watched history.