<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Deep Learning | Tuhin Sharma</title><link>https://tuhinsharma.netlify.app/tags/deep-learning/</link><atom:link href="https://tuhinsharma.netlify.app/tags/deep-learning/index.xml" rel="self" type="application/rss+xml"/><description>Deep Learning</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sun, 19 May 2024 14:15:00 +0000</lastBuildDate><image><url>https://tuhinsharma.netlify.app/media/icon_hu55b84836e614877e119cbfa37f6d5a66_1386708_512x512_fill_lanczos_center_3.png</url><title>Deep Learning</title><link>https://tuhinsharma.netlify.app/tags/deep-learning/</link></image><item><title>Revolutionizing Smart Buildings with Federated Learning</title><link>https://tuhinsharma.netlify.app/blogs/federated-learning/</link><pubDate>Sun, 19 May 2024 14:15:00 +0000</pubDate><guid>https://tuhinsharma.netlify.app/blogs/federated-learning/</guid><description>&lt;h2>Description&lt;/h2>
&lt;p>In today’s world, IoT (Internet of Things) devices are integral to our daily lives. From wearables and self-driving cars to smart buildings and cities, these devices shape and control our environments. Among these innovations, smart buildings stand out by not only ensuring the comfort and safety of occupants but also promoting energy and financial efficiency. The integration of AI (Artificial Intelligence) in smart buildings has made them even smarter by leveraging data from various sensors to optimize building functionalities.&lt;/p>
&lt;p>&lt;a href="https://medium.com/@tuhinsharma121/raptor-a-smarter-way-to-retrieve-and-use-information-in-ai-fd3cb68a6f2f">&lt;p>&lt;strong>Read more..&lt;/strong>&lt;/p>&lt;/a>&lt;/p></description></item><item><title>Logo detection using Apache MXNet</title><link>https://tuhinsharma.netlify.app/blogs/logo-mxnet/</link><pubDate>Thu, 01 Feb 2018 14:15:00 +0000</pubDate><guid>https://tuhinsharma.netlify.app/blogs/logo-mxnet/</guid><description>&lt;h2>Description&lt;/h2>
&lt;p>Given an image, identify which company&amp;rsquo;s logo is present.&lt;/p>
&lt;p>The article will motivate the business problem, how to get data, how to use MXNet to build the deep learning model&lt;/p>
&lt;p>&lt;a href="https://www.oreilly.com/ideas/logo-detection-using-apache-mxnet">&lt;p>&lt;strong>Read more..&lt;/strong>&lt;/p>&lt;/a>&lt;/p></description></item><item><title>Uncovering hidden patterns through machine learning</title><link>https://tuhinsharma.netlify.app/blogs/fizzbuzz-mxnet/</link><pubDate>Thu, 21 Dec 2017 14:15:00 +0000</pubDate><guid>https://tuhinsharma.netlify.app/blogs/fizzbuzz-mxnet/</guid><description>&lt;h2>Description&lt;/h2>
&lt;p>FizzBuzz problem was made popular by Joel Grus&amp;rsquo; &lt;a href="https://joelgrus.com/2016/05/23/fizz-buzz-in-tensorflow/">post&lt;/a> on tensorflow. This article shows how to model fizzbuzz using MXNet. This article shows how to use the basic building blocks of MXNet (autograd etc.) to build a network from scratch. It then goes to show how to use higher level APIs in MXNet to achieve the same.&lt;/p>
&lt;p>&lt;a href="https://www.oreilly.com/radar/uncovering-hidden-patterns-through-machine-learning/">&lt;p>&lt;strong>Read more..&lt;/strong>&lt;/p>&lt;/a>&lt;/p></description></item></channel></rss>