https://dhruvs.space/enContents © 2020 <a href="mailto:dhruvt93@gmail.com">Dhruv Thakur</a> Fri, 14 Feb 2020 22:35:36 GMTNikola (getnikola.com)http://blogs.law.harvard.edu/tech/rsshttps://dhruvs.space/posts/visualizing-convolutions-part-1/Dhruv Thakur<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt"> </div><div class="inner_cell"> <div class="text_cell_render border-box-sizing rendered_html"> <p>I'm currently learning about Convolutional Neural Nets from <a href="https://deeplearning.ai">deeplearning.ai</a>, and boy are they really powerful. Some of them even have cool names like <a href="https://www.cs.unc.edu/~wliu/papers/GoogLeNet.pdf">Inception Network</a> and make use of algorithms like <a href="https://arxiv.org/pdf/1506.02640">You Only Look Once (YOLO)</a>. That is hilarious and awesome.</p> <p>This notebook/post is an exercise in trying to visualize the outputs of the various layers in a CNN. Let's get to it.</p> <p><a href="https://dhruvs.space/posts/visualizing-convolutions-part-1/">Read more…</a> (13 min remaining to read)</p></div></div></div>convnetsdeep-learningkerasneural-netshttps://dhruvs.space/posts/visualizing-convolutions-part-1/Mon, 24 Sep 2018 13:14:21 GMThttps://dhruvs.space/posts/understanding-forward-and-backpropagation/Dhruv Thakur<div><p>I recently completed the <a href="https://www.coursera.org/learn/neural-networks-deep-learning">first</a> course offered by <a href="https://www.deeplearning.ai/">deeplearning.ai</a>, and found it incredibly educational. Going forwards, I want to keep a summary of the stuff I learn (for my future reference) in the form of notes like this. This one is for forward and back-prop intuitions.</p> <p><a href="https://dhruvs.space/posts/understanding-forward-and-backpropagation/">Read more…</a> (3 min remaining to read)</p></div>deep-learningmachine-learningneural-netssummary-noteshttps://dhruvs.space/posts/understanding-forward-and-backpropagation/Mon, 10 Sep 2018 10:55:00 GMT