Building Neural Networks from Scratch Lecture 15 - Finding derivatives of inputs in backpropagation and why we need them
Lecture 15 - Finding derivatives of inputs in backpropagation and why we need them Transcript and Lesson Notes
In this lecture, we look at how to calculate derivatives of inputs in backpropagation. Along with the weight derivatives, it is also important to calculate the input derivatives. Why? Because inputs of one layer are the
Quick Summary
In this lecture, we look at how to calculate derivatives of inputs in backpropagation. Along with the weight derivatives, it is also important to calculate the input derivatives. Why? Because inputs of one layer are the
Key Takeaways
- Review the core idea: In this lecture, we look at how to calculate derivatives of inputs in backpropagation. Along with the weight derivatives, it is also important to calculate the input derivatives. Why? Because inputs of one layer are the
- Understand how lecture fits into Lecture 15 - Finding derivatives of inputs in backpropagation and why we need them.
- Understand how finding fits into Lecture 15 - Finding derivatives of inputs in backpropagation and why we need them.
- Understand how derivatives fits into Lecture 15 - Finding derivatives of inputs in backpropagation and why we need them.
- Understand how inputs fits into Lecture 15 - Finding derivatives of inputs in backpropagation and why we need them.
Key Concepts
Full Transcript
In this lecture, we look at how to calculate derivatives of inputs in backpropagation. Along with the weight derivatives, it is also important to calculate the input derivatives. Why? Because inputs of one layer are the outputs of the previous layer, and in backpropagation, outputs of the previous layer are needed. We implement everything from scratch: first through writing on a whiteboard, and then through code. 0:00 Problem formulation 7:13 Chain Rule 16:21 Matrix formulation 21:18 Batch of input data ================================================= ✉️ Join our FREE Newsletter: https://vizuara.ai/our-newsletter/ ================================================= As we learn AI/ML/DL the material, we will share thoughts on what is actually useful in industry and what has become irrelevant. We will also share a lot of information on which subject contains open areas of research. Interested students can also start their research journey there. Students who are confused or stuck in their ML journey, maybe courses and offline videos are not inspiring enough. What might inspire you is if you see someone else learning and implementing machine learning from scratch. No cost. No hidden charges. Pure old school teaching and learning. ================================================= 🌟 Meet Our Team: 🌟 🎓 Dr. Raj Dandekar (MIT PhD, IIT Madras department topper) 🔗 LinkedIn: https://www.linkedin.com/in/raj-abhijit-dandekar-67a33118a/ 🎓 Dr. Rajat Dandekar (Purdue PhD, IIT Madras department gold medalist) 🔗 LinkedIn: https://www.linkedin.com/in/rajat-dandekar-901324b1/ 🎓 Dr. Sreedath Panat (MIT PhD, IIT Madras department gold medalist) 🔗 LinkedIn: https://www.linkedin.com/in/sreedath-panat-8a03b69a/ 🎓 Sahil Pocker (Machine Learning Engineer at Vizuara) 🔗 LinkedIn: https://www.linkedin.com/in/sahil-p-a7a30a8b/ 🎓 Abhijeet Singh (Software Developer at Vizuara, GSOC 24, SOB 23) 🔗 LinkedIn: https://www.linkedin.com/in/abhijeet-singh-9a1881192/ 🎓 Sourav Jana (Software Developer at Vizuara) 🔗 LinkedIn: https://www.linkedin.com/in/souravjana131/
Lesson FAQs
What is Lecture 15 - Finding derivatives of inputs in backpropagation and why we need them about?
In this lecture, we look at how to calculate derivatives of inputs in backpropagation. Along with the weight derivatives, it is also important to calculate the input derivatives. Why? Because inputs of one layer are the
What key concepts are covered in this lesson?
The lesson covers lecture, finding, derivatives, inputs, backpropagation.
What should I learn before Lecture 15 - Finding derivatives of inputs in backpropagation and why we need them?
Review the previous lessons in Building Neural Networks from Scratch, then use the transcript and key concepts on this page to fill any gaps.
How can I practice after this lesson?
Practice by applying the main concepts: lecture, finding, derivatives, inputs.
Does this lesson include a transcript?
Yes. The full transcript is visible on this page in indexable HTML sections.
Is this lesson free?
Yes. CourseHive lessons and courses are available to learn online for free.
Continue Learning
Continue this lesson in the app
Install CourseHive on Android or iOS to keep learning while you move.
