In the previous session, you explored the basics of an extensive library called Tensorflow to help build and train neural networks with ease and used it to implement the housing price prediction example.
In this session
You will continue working with Tensorflow and will learn about how to reshape tensors and calculate gradients.
The objectives of this session include the following:
- Reshaping and Broadcasting
- Computational Graphs and Gradients
- Minimise Functions
- TensorFlow Architecture
- TensorFlow Playground
During the session, there will be small coding challenges that you can attempt in order to become fluent with TensorFlow.
Guidelines for In-Module Questions
The in-video and in-content questions for this module are not graded. Note that graded questions are provided in a separate segment titled ‘Graded Questions’ at the end of this module. These questions will adhere to the guidelines provided below.
| First Attempt Marks | Second Attempt Marks | |
| Question with 2 attempts | 10 | 05 |
| Question with 1 attempt | 10 | 0 |
People, you will hear from in this session
Subject Matter Expert
Dr Avishek Pal
Senior Data Scientist at Microsoft
Avishek has more than 12 years of experience in the data science and software industry and has worked for companies such as IBM, Ericsson and Fidelity Investments. He completed his PhD in Industrial and Systems Engineering from the University of Warwick, UK. Avishek’s current work at Microsoft includes mining massive data sets to generate rich content to improve the local search experience on Bing for Great Britain, France, Germany, Austria and India. He leads the India time zone of the Microsoft WorldWide ML community.
Data Science Consultant
Usha works as a data science consultant at Infinite-Sum Modelling Inc. She has more than 4 years of experience in the field of deep learning and is the chapter lead for the TensorFlow User Group and Google Developers Group Mysore. She is also the co-organiser of Women in Machine Learning & Data Science, Bengaluru Chapter.
Report an error