Posts

Showing posts with the label Convolutional Neural Networks
Career skills to jumpstart your future.

Honest review of the Deep Learning Specialization by deeplearning.ai

Image
What is Deep Learning Specialization? The Deep Learning Specialization is the group of courses by Andrew Ng and his staff over at deeplearning.ai, which is a comprehensive course that starts at the extreme basics of Neural Networks (a part of Machine Learning) and ends up teaching you concepts applicable in various cutting-edge fields of AI. If you haven't yet learnt from Andrew Ng, all I can say is you're in for a ride! His teaching is excellent and the learner's understanding is ensured. I have done all four courses, with 100% grade and certification, and will review them below. But before that... Proof 1.   Neural Networks and Deep Learning This course is intended to teach you what is Deep Learning  and what it means to the technology world. Although the course starts with Logistic Regression, the course eventually ends up training first shallow Neural Networks and then deep NNs. If you have never done an AI course, no worries this course got you covered....

LightSpeed Intro to ConvNets

Image
LightSpeed intro to ConvNets ________________________________________________ Unless you're experienced or have read the LightSpeed intro to DL, please see here before reading this. --------------------------------------------------------------------------------- In this post, you'll learn about- What are Convolutions? Why Convolutions work great (optional) Keras and TensorFlow (compulsory) How to make a Neural Network that can classify pictures depending on objects! What are ConvNets? Now, what are  ConvNets ? They are Neural Networks having Convolutions. Okay, so what are Convolution s ?  Convolutions, informally, are mathematical functions. Now, to convolve the above matrices, we take the second smaller matrix, then we imprint it on the first possible 2 by 2 chunk of the other as shown below. So, this will be the first value in the output matrix- = (4*1) + (2*0) + (0*0) + (3*1) = 7 Similarly, you may be able to calculate that the next ...