Artificial Intelligence (AI)

• Introduction to Artificial Intelligence
• Fundamentals of Artificial Intelligence
• Applications of Artificial Intelligence
• Future of Artificial Intelligence
• Neural Network Introduction (Intuition behind Artificial Intelligence)
• Practical examples (Introduction to Numpy, Pandas and sci- kitlearn)

• Building block for Neural Networks
• Single NN
• Input/output Mapping
• Type Activation Functions
• Neural Network Architecture
• Practical examples (Introduction to ANN APIs and libraries)

• EDA / Data wrangling
• Back Propagation
• Loss Functions
• Hyperparameter Optimization
• Gradient

• Convolutional Neural Network
• Computer Vision real life application
• Overfitting/Underfitting
• NN issues (vanishing gradients etc)
• Model improvement and generalization techniques (Data Augmentation, Dropout, batch Normalization etc.)

• Recurrent Neural Network
• RNN variants (LSTMs etc)
• BI basic idea and importance

• BI tools and techniques (Power BI hands on)
• Introduction to Flask APIs
• Practical Project

• BI tools and techniques (Power BI hands on)
• Introduction to Flask APIs
• Practical Project

• Natural Language Processing and its essential libraries e.g. NLTK
• Tokenizing Text, Filtering Stop words, stemming and lemmatization
• Basic of Part of Speech, Word Embedding
• PCA
• Project Mid quires and discussion

• Time series prediction
• Feature Engineering
• Feature Extraction
• Feature Importance

• Big Data introduction and basic
• Offline/Online warehouse
• OLAP/OLTP
• Project final evaluation and discussion

Upon completion of this course, participants will be able to:                    

• Understand the fundamental concepts of Artificial Intelligence (AI), Neural Networks, Deep Learning, Natural Language Processing etc.
• Build, train, and deploy different types of predictive models with respect to industry best practices and large-scale real- world application requirements.
• Application of Deep Learning to real-world scenarios such as object recognition and Computer Vision, image and video processing, text analytics, Natural Language Processing, recommender systems, and other types of classifiers.
• Master Deep Learning at scale with accelerated hardware and GPUs.              
• Use of popular Deep Learning libraries such as Keras, PyTorch, and Tensorflow applied to industry problems.
• Integrate the AI based predictive models into professional applications for real time predictions.