AIML Foundation Module
1
Evelyn Benedict
Appreciation of different aspects of AIML 1. What is AI and how machines learn - concept and the m...
COURSE OVERVIEW
It may not be visible but today algorithms are all around us. They’re in the cell phone, in the laptop, in the car, in the house and even in the toys. The banks run on algorithms, airlines and factories run on algorithms. In this course we try to understand what these algorithms are and more importantly, how we can generate these algorithms ourselves; not in the conventional way of coding but making the machine learn how to code themselves. It would not only enable us to do more but also enable us to generate more algorithms which are too complex. And it would be faster, possibly cheaper and definitely more versatile. By more versatile I mean doing things that machines have not been able to do with conventional programming, think like helping computers see and understand human language and sense several other things in the environment. Sounds quite interesting. So, let us start our journey. Hope by the end of the course you would have a much deeper understanding of what is artificial intelligence and machine learning and how we can make use of it in our daily lives and in our business. Not only to make things faster and easier but also to do transformative things which may not appear possible now.
| Overview of AIML | Overview of AIML 1. A brief history 2. What has changed in recent years 3. Why AIML has become a powerful force of change 4. How it can be applied in various domains 5. What we expect over the next few years |
| Different types of Machine Learning | 1. Supervised Learning Regression Classification 2. Unsupervised Learning Clustering Dimensionality Reduction 3. Deep Learning - brief introduction to Artificial Neural Networks Recurrent Neural Networks Convolutional Neural Networks Generative Networks 4. Reinforcement Learning Understanding the suitability, pros and cons of using various algorithms for different types of business problems. |
| Application of Deep Learning | 1. Conventional areas - making predictions, classification, regression ... 2. Natural Language processing 3. Computer vision How different deep learning architectures make it possible. |
| Demystifying AIML | Working with one sample problem - getting a feel of how to train machines to learn |
| Lifecycle of creating a solution | Understanding the lifecycle stages of AIML and how it differs from conventional IT projects. Appreciation of changes needed in skills and mindset. 1. Problem formulation 2. Data Preparation 3. Model Selection 4. Feature Engineering 5. Model optimisation |
| Performance Metrics | RMSE, Precision, Recall, F1-Score, Accuracy |
.
AVAILABLE SUBSCRIPTION PLANS
| 2 month | ₹ 14999 |
Evelyn Benedict
