Generative Adversarial Networks for Data Augmentation (AI)
- Description
- Curriculum
- FAQ
- Reviews
AI is an enabler in transforming diverse realms by exploiting deep learning architectures.
The course aims to expose students to cutting-edge algorithms, techniques, and codes related to AI and particularly the Generative Adversarial Networks used for data creation in deep learning routines. This course encompasses multidimensional implementations of the themes listed below;
1. Deep Learning: A subset of Hybrid Artificial Intelligence
2. Big Data is Fueling Applied AI.
3. How to model a problem in AI using datasets in Python (Keras & TensorFlow Libraries).
4. Data Augmentation using GANs in Hybrid Deep Learning Networks.
5. How to use Transfer Learning in Hybrid GAN Networks.
6. How to use transfer learning in multiclass classification healthcare problems.
6. Backward Propagation and Optimization of hyper-parameters in AI GANs.
7. Leading Convolutional Neural Networks (ALEXNET & INCEPTION) using GANs and validation indices.
8. Recurrent Neural Networks extending to Long Short Term Memory.
9. An understanding of Green AI.
10. Implementations of Neural Networks in Keras and Pytorch and introduction to Quantum Machine Learning.
11. Algorithms related to Quantum Machine Learning in TensorFlow Quantum and Qiskit.
12. GANs for Neurological Diseases using Deep Learning.
13. GANs for Brain-Computer Interfacing and Neuromodulation.
14, GAN based AI algorithms for diagnosis, prognosis, and treatment plans for Tumors.
15. How to model an AI problem using GAN in Healthcare.
16. AI in BlockChain and Crypto mining
17 AI in Crypto trading.
18. Forks in Block Chain via AI.
19. Investment Strategies in Crypto- trade using AI (Fungible and Non- Fungible Digital Currencies).
24. Artificial Intelligence in Robotics- A case example with complete code.
25. Artificial Intelligence in Smart Chatbots- A case example with complete code.
26. Impact of AI in business analytics- A case example with complete code.
27. AI in media and creative industries- A case example with complete code.
28. AI based advertisements for maximum clicks- A case example with complete code.
29. AI for the detection of Misinformation Detection.
30. Extraction of Fashion Trends using AI.
31. AI for emotion detections during Covid- 19.
-
1
Deep Machine Learning- A subset of AIThe students would learn in this lecture about what is Machine Learning, types of Machine Learning and case examples regarding Neural Networks and Deep Learning algorithms
-
2
Role of Big Data Computing in AI
This lecture shall familiarize students with "Big Data", how it works, types and its relevance to AI Healthcare problems.
-
14
Long Short Term Memory using Recurrent Neural Networks for Bio-computing
The students shall learn about the LSTM and its variants in terms of information storage
-
15
Tiny Artificial Intelligence for well being using Wearables and Implants
This lecture would focus on the Tiny AI healthcare chips promises to pack more computational power and train and run AI at lesser energy levels
-
16
Emerging AI Healthcare Landscape
This lecture would focus on emerging healthcare landscape and role of Natural Language Processing (NLP) and Python language packages including Django and Flask
-
17
Artificial Intelligence Nurturing Healthcare
In this lecture students shall learn about AI functionalities, examples and types. Students would be introduced to the factors refueling AI.
