--> Various Projects as a part of Nanodegree curriculum . --> Notebooks lead implementing models such as convolutional networks, recurrent networks, and GANs.
- Sentiment Analysis with Numpy: building a sentiment analysis model, predicting if some text is positive or negative.
- Intro to TensorFlow: Starting building neural networks with Tensorflow.
- Autoencoders: Build models for image compression and denoising, using feed-forward and convolution networks in TensorFlow.
- Transfer Learning (ConvNet). Training large network on huge datasets using pretrained networks such as VGGnet.Used VGGnet to classify images of flowers without training a network on the images themselves.
- Intro to Recurrent Networks (Character-wise RNN): Recurrent neural networks are able to use information about the sequence of data, such as the sequence of characters in text.
- Embeddings (Word2Vec): Implement the Word2Vec model to find semantic representations of words for use in natural language processing.
- Sentiment Analysis RNN: Implement a recurrent neural network that can predict if a text sample is positive or negative.
- Learning Keras :Student Admit prediction using keras.
- Character Sequence : Using RNN for text generation
- Reinforcement Learning (Q-Learning): Implement a deep Q-learning network to play a simple game from OpenAI Gym.
- Deep Reinforcement Learning: policy gradient actor critic method
- Monte Carlo: Monte Carlo for continuous task .
- Temporal Differnce: Temporal Difference for continuous task.
- Dynamic Programming Agent: Frozen lake environment for Deep Reinforcement Learning.
- Convolutional Neural Network: Implementing CNN for CIFAR dataset .
- Generative Adversatial Network on MNIST: Train a simple generative adversarial network on the MNIST dataset.
- Deep Convolutional GAN (DCGAN): Implement a DCGAN to generate new images based on the Street View House Numbers (SVHN) dataset.
- First Neural Network: Implement a neural network in Numpy to predict bike rentals.
- Image classification: Build a convolutional neural network with TensorFlow to classify CIFAR-10 images.
- Text Generation: Train a recurrent neural network on scripts from The Simpson's (copyright Fox) to generate new scripts.
- Quadcopter fly: Using deep reinforcement learning , make a quadcopter fly
- Face Generation: Use a DCGAN on the CelebA dataset to generate images of novel and realistic human faces.