Deep Learning for Natural Language Processing

Palash Goyal works as Senior Data Scientist, and is currently working with the applications of Data Science and Deep Learning in Online Marketing domain. He studied Mathematics and Computing from IIT-Guwahati, and proceeded to work in a fast, upscale environment.He holds wide experience in E-Commerce, Travel, Insurance, and Banking industries. Passionate about mathematics and Finance, in his free time he manages his portfolio of multiple Cryptocurrencies and latest ICOs using Deep Learning and Reinforcement Learning techniques for price prediction and portfolio management.He keeps himself in touch with the latest trends in the Data Science field and pen it down on his personal blog and digs articles related to Smart Farming in left over time.

Karan Jain is Product Analyst at Sigtuple , where he works on cutting edge AI driven diagnostic products . Before which he worked as a Data Scientist at Vitrana Inc , a healthcare solutions company.He enjoys working in fast culture and data-first start ups. In his leisure time he deeps dive into Genomics sciences, BCI interfaces , Optogenetics . He recently developed interest in POC devices and Nano tech for further portable diagnosis. He has healthy network of 3000+ followers on linkedin.

Sumit Pandey is a graduate from IIT Kharagpur. He worked for about a year with AXA Business services as a Data Science Consultant. He is currently engaged in launching his own venture.

Chapter
1: Introduction to NLP and Deep LearningChapter Goal: Introduction of Deep Learning and NLP concepts, explanation of the evolution of deep learning and comparison of deep learning with other machine learning techniques in PythonNo of pages: 50-60Sub -Topics
1. Deep Learning Framework - An overview
2. Comparison with other machine learning techniques
3. Why Python for Deep Learning
4. Deep Learning Libraries
5. NLP- An overview
6. Introduction to Deep Learning for NLP
Chapter
2: Word Vector representationsChapter Goal: Introduction of basic and advanced word vector representationNo of pages: 50-60Sub - Topics
1. Overview of Simple Word Vector representations: word2vec, Glove
2. Advanced word vector representations: Word Representations via Global Context and Multiple Word Prototypes
3. Evaluation methods for unsupervised word embedding
Chapter
3: Neural Networks and Back Propagation Chapter Goal: Neural Networks for named entity recognitionNo of pages: 50-60Sub - Topics:
1. Learning Representations by back propagating the errors
2. Gradient checks, over-fitting, regularization, activation functions
Chapter
4: Recurrent neural networks, GRU, LSTM, CNNChapter Goal: Deep Learning architectures like RNN, CNN, LSTM, and CNN in great details with proper examples of eachNo of pages: 70-80Sub - Topics:
1. Recurrent neural network based language model
2. Introduction of GRU and LST
M3. Recurrent neural networks for different tasks
4. CNN for object identification

Chapter
5: Developing a ChatbotChapter Goal: Chatbots are artificial intelligence systems that we interact with via text or voice interface. Our aim is to develop and deploy a Facebook messenger Chatbot.No of pages: 50-60Sub - Topics:
1. Development of a simple closed context Chatbot
2. Deployment using free server "Heroku"
3. Integrating Seq2seq model with the Chatbot
4. Integrating Image Identification model with the ChatbotChapter
6: Interaction of Reinforcement Learning and ChatbotChapter Goal: Detailed explanation of the Reinforcement Learning concept and one of the prevalent case studies/research paper on Reinforcement Learning applications for ChatbotNo of pages: 20-30Sub - Topics:
1. Introduction to Reinforcement Learning
2. Present applications of Reinforcement Learning for Chatbot
3. Detailed explanation of one of the research papers on applications of Reinforcement Learning for Chatbot