Explained about Gradient Descent optimizer, Stochastic gradient Descent optimizer and Mini Batch Stochastic Descent Optimizer in details with proper example and related Maths.
Stochastic gradient descent (SGD) calculates the gradient (direction) using a single sample. Means it calculate loss on the basis of single record and then update the weight based on that loss. Due to its stochastic nature, the path towards the global minima is not "direct" as in GD, but may go "zig-zag"..
Mini-Batch Gradient Descent combines the best of both to converge faster with less computational overhead. In this video, I'll talk about all the 3 Optimizers( Gradient Descent Optimizer, SGD and Mini batch SGD) so that the concept is clear.
If you do have any questions with what we covered in this video then feel free to ask in the comment section below & I'll do my best to answer your queries.
Please consider clicking the SUBSCRIBE button to be notified for future videos & thank you all for watching.
Channel: https://www.youtube.com/channel/UCgHDngFV50KmbqF_6-K8XhA
Support my channel 🙏 by LIKE ,SHARE & SUBSCRIBE
Check the complete Machine Learning Playlist : https://www.youtube.com/playlist?list=PLv8Cp2NvcY8CoxylKNIYBd9ZVQ1SlFWQ3
Check the complete Deep Learning Playlist :
https://www.youtube.com/playlist?list=PLv8Cp2NvcY8CaSVfCIyg5mvek8JvaD7tE
Subscribe my channel: https://www.youtube.com/channel/UCgHDngFV50KmbqF_6-K8XhA
Support my channel 🙏🙏🙏🙏🙏🙏🙏🙏 by LIKE ,SHARE & SUBSCRIBE
Contact: [email protected]
#gradientdescent #Batchgradientdescent #Stochasticgradientdescent #PifordTechnologies #AI #ArtificialIntelligence #DeepLearning
