Rishit Dagli - Authoring

Writing and being able to share my knowledge fascinates me, I find it really interesting to be able to impact ~ 200 K readers through these articles.

The Ferromagnetic Potts ModelThe ferromagnetic Potts model is a canonical example of a Markov random field from statistical physics that is of great probabilistic and algorithmic interest. This is a distribution over all 1-colorings of the vertices of a graph where monochromatic edges are favored. The algorithmic problem of efficiently sampling approximately from this model is known to be #BIS-hard, and has seen a lot of recent interest. This blog outlines some recently developed algorithms for approximately sampling from the ferromagnetic Potts model on d-regular weakly expanding graphs.

Review of Domain Generalization using Causal Matching: Causal Learning SeriesIn this part of the causal learning series I will review the paper Domain Generalization using Causal Matching. This was also submitted as an assignment at the University of Toronto.

Compression techniques in Statistical LearningCharacterizing the sample complexity of different machine learning tasks is one of the central questions in statistical learning theory. This blog reviews the less conventional approach of using compression schemes for proving sample complexity upper bounds, with specific applications in learning under adversarial perturbations and learning Gaussian mixture models.

How to Use GitHub Super Linter in Your ProjectsWhen you're starting a new project, you might have to add multiple linting tools to beautify your code and prevent simple errors. You will often use multiple linters – one of them might support an npm installation and other one might have a PyPI installation and so on. You

10 min read on freeCodeCamp

Kubeflow Pipelines: Orchestrating Machine Learning Workflows - Part 3Kubeflow Pipelines is a great way to build and deploy end-to-end scalable and portable Machine Learning workloads. In this article, we take a look at how to use Kubeflow Pipelines for your own tasks and how Kubeflow Pipelines works under the hood. Pr...

16 min read on Kubesimplify

Kubeflow Notebooks: ML Experimentation Made Easier - Part 2Machine learning is a very iterative process with a ton of experimentation you might need to do. In this article, I introduce you to Kubeflow Notebooks, a way to run development environments inside your Kubernetes cluster, as well as how you could ex...

13 min read on Kubesimplify

Kubeflow: Machine Learning on Kubernetes - Part 1Developing and deploying machine learning systems could be a pain with multiple things you need to manage. In this article, I introduce you and help you get started with Kubeflow while also understanding how Kubeflow works. This is the first article ...

11 min read on Kubesimplify

My first in-person KubeCon + CloudNativeCon | Cloud Native Computing FoundationCommunity post by Rishit Dagli This year I got a chance to attend my first in-person KubeCon + CloudNativeCon in Valencia, Spain under the generous Dan Kohn scholarship by CNCF and Linux Foundation.

15 min read on CNCF Blog

What Are Graph Neural Networks? How GNNs Work, Explained with ExamplesGraph Neural Networks are getting more and more popular and are being used extensively in a wide variety of projects. In this article, I help you get started and understand how graph neural networks work while also trying to address the question "why" at each stage. Finally we

15 min read in freeCodeCamp

A New Short but Interesting Number Theory Theorem

How to Start an Open Source Project on GitHub – Tips from Building My Trending RepoDevelopers around the world use GitHub to share their projects with the global developer community. In this article, I'll give you some opinionated tips to help you build a great open-source project you can start using. You can also use these tips for building hackathon projects. Quite recently I ended

12 min read in freeCodeCamp

Keras documentation: Self-supervised contrastive learning with NNCLR

Authored a TensorFlow Keras Example

Keras documentation: Image classification with Swin Transformers

Authored a TensorFlow Keras Example

How to Monitor Machine Learning Projects on Your Mobile Device📱What if you could monitor your Colab, Kaggle, or AzureML Machine Learning projects on your mobile phone? You'd be able to check in on your models on the fly – even while taking a walk🚶. If you are an ML developer, you know how training models can easily take a long

6 min read in freeCodeCamp

Student Diaries: My Journey – How I got into research and AIAn inspiring article at APF written by Rishit sheds light onto his journey to the world of AI and Machine Learning. He mentions with utmost sincerity as to how tons of free resources are available …

Job Descriptions Keyword Extraction using Attention based Deep Learning Models with BERT

Authored a paper published in IEEE

Deploying a smart queuing system on edge with Intel OpenVINO toolkit

Authored a paper published in Springer

Keras documentation: Gradient Centralization for Better Training Performance

Authored a TensorFlow Keras Example

Plant AI: Student Ambassador Green-A-Thon activity report Hello developers ! In this article, we introduce our project “Plant AI ” and walk you through our motivation behind building this project, how it could be helpful to the community, the process of building this project, and finally our future plans with this project. Plant AI is a web applicatio...

10 min read in Microsoft Developer Blog

Skewness and Kurtosis – Positively Skewed and Negatively Skewed Distributions in Statistics ExplainedIn this article, I'll explain two important concepts in statistics: skewness and kurtosis. And don't worry – you won't need to know very much math to understand these concepts and learn how to apply them. What are Density Curves?Let's first talk a bit about density curves, as skewness and kurtosis

11 min read in freeCodeCamp

Deploying a Smart Queuing System on Edge with Intel OpenVINO ToolkitRecent increases in computational power and the development of specialized architecture led to the possibility to perform machine learning, especially inference, on the edge. OpenVINO is a toolkit based on Convolutional Neural Networks that facilitates fast-track development of computer vision al...

Paper Preprint

How to Build Better Machine Learning ModelsHello developers 👋. If you have built Deep Neural Networks before, you might know that it can involve a lot of experimentation. In this article, I will share with you some useful tips and guidelines that you can use to better build better deep learning models. These tricks should make it

10 min read in freeCodeCamp

How to Build Better Machine Learning ModelsHello developers 👋. If you have built Deep Neural Networks before, you might know that it can involve a lot of experimentation. In this article, I will share with you some useful tips and guidelines…

11 min read in Towards Data Science

The Art of Hyperparameter Tuning in Deep Neural Nets by Example🎨Hello developers 👋, If you have worked with Deep Neural Networks earlier that changing neural nets can involve setting a lot of different…

12 min read in Towards Data Science

Daily Newsletter — 23rd December 2020Low light image enhancement, a platform for real-time data-driven decision making and a visual guide for NumPy in today’s Data Science…

Featured in JovianML

Android Newsletter #24Hey folks, in this week's edition of Android Newsletter, you'll 🚀 Write better tests with JUnit 5 🎮 Build a game with Jetpack Compose 🤖 Add machine learning to your app ⚡ Disable Jetifier to improve the build time, and much more! Enjoy, and see you next week. How

Featured in the Android Newsletter #24

Machine Learning with Android 11! What’s newBy Rishit Dagli This blog demonstrates how you can get started with on-device ML with tools or plugins specifically launched with Android 11. If you have earlier worked with ML in Android, you will explore easier ways to integrate your ML applications with your Android apps.

11 min read in Droidcon

TensorFlow Tip, Optimize your Training💡 #TensorFlowTip Use .prefetch to reduce your step time of training and extracting data overlap the preprocessing and model execution while the model executes training step n the input pipeline is reading the data for n+1 step reduces the idle time...

Android Weekly - Free weekly Android & Kotlin development newsletterAndroid Weekly - Free weekly Android & Kotlin development newsletter

Featured in the Android Weekly #444

Android Weekly - Free weekly Android & Kotlin development newsletterAndroid Weekly - Free weekly Android & Kotlin development newsletter

Featured in the Android Weekly #442

Machine Learning with Android 11: What’s newThis blog demonstrates how you can get started with on-device ML with tools or plugins specifically launched with Android 11. If you have…

10 min read in ProAndroidDev

Set up an Android development environment in GCPBy Rishit Dagli This blog is equally contributed to by preet parekh. This blog has now also been published on Official Google Cloud Tutorials. You have probably seen this image below, it's quite popular by the way. And you too might have faced issues like Android Studio is very slow, build takes a lot of time, AVD starts after a long time if you are on a slow machine like mine.

10 min read in Droidcon

TensorFlow User Groups: Updates from Around the World

Featured in official TensorFlow Blog

Featured in Google's Community Leads Platform

Machine Learning with Android 11: What’s newThis blog demonstrates how you can get started with on-device ML with tools or plugins specifically launched with Android 11. If you have…

10 min read in Towards Data Science

Working with Complex Image data for CNNsThis is the fifth part of Deep Learning with TensorFlow where you’ll see how you can work with real life complex image data in TensorFlow

5 min read

Set up an Android development environment on Compute Engine

Published in Google Cloud tutorials

A State of the Art Coding Problem

I recently came across a State of the Art (SOTA) problem according to me. How I define a problem to be really good-

Deploying models to production with TensorFlow model serverDeploy models and serve them to users without worrying about infrastructure with TF Model Server

10 min read in Towards Data Science

Building Better AI Apps with TF HubOne of the best things about AI is that you have a lot of open-source content, we use it quite frequently. I will show how TensorFlow…

10 min read in Towards Data Science

Solving Overfitting in Neural Nets With RegularizationLearn about how you could implement regularization to solve overfitting in your DNNs and also understand the intuitions behind them

10 min read in Towards Data Science

Vanishing/ Exploding Gradients in Deep Neural Nets and solving themUnderstanding the problem of vanishing/exploding gradients in Deep Neural Networks and novel methods to solve them

10 min read in The Startup (Largest active Publication)

Debugging your Neural Nets and checking your GradientsUnderstand how you could debug your neural networks and easily find errors in them with Gradient Checking

10 min read in Towards Data Science

Tips to building better Deep Learning Models from 10 Days of ML ChallengeThese tips are gathered when I was participating in 10 Days of ML Challenge, a wonderful initiative by TensorFlow User Group Mumbai to…

10 min read in Towards Data Science

Getting started with Kotlin for Data Science and AIData science is a quite exciting field, you are trying to figure out some patterns in your data, make some cool plots from your data and…

5 min read in Kotlin Mumbai

Getting started with Deep Learning in browser with TF.jsIf you are a beginner in Machine Learning and want to get started with developing models in the browser this is for you, if you already…

Part 1, 5 min read in Analytics Vidya

Getting started with Deep Learning in browser with TF.jsIf you are a beginner in Machine Learning and want to get started with developing models in the browser this is for you, if you already…

Part 2, 5 min read in Analytics Vidya

My experience at Ignited Minds Expo 2020An annual tech event which witnessed 5000+ participation

5 min read

Extending what Convolutional nets can doThis is the fourth part of the series where I post about TensorFlow for Deep Learning and Machine Learning

8 min read

Using Convolutional Neural Networks with TensorFlow Part-3This is the third part of the series where I post about TensorFlow for Deep Learning and Machine Learning. In the earlier blog post you…

10 min read

Set up a Android development environment in GCPAndroid studio on Cloud

9 min read in ProAndroidDev

Get started with TensorFlow and Deep Learning Part-1This is the first part of a series where I will be posting many blog posts about coding Machine Learning and Deep Learning algorithms. I…

10 min read

Computer Vision with TensorFlow Part-2This is the second part of the series where I post about TensorFlow for Deep Learning and Machine Learning. In the earlier blog post you…

12 min read

Build K-Means from scratch in PythonIntroduction to K-means Clustering

6 min read

Circuit Creation in CircuitVerse from scratchOK, so what’s CircuitVerse?

6 min read

Connecting Processing and Arduino to Make 7 Segment and Servo GUI ControllerFor some projects you made need to use Arduino as it provides an easy prototyping platform but displaying graphics in serial monitor of…

5 min read

Create Logistic Regression algorithm from scratch and apply it on data setPrerequisites

5 min read

Going Beyond Academics – The Story of A Young InnovatorRishit Dagli is competent in various programming languages such as C, C++, Java, Python, along with Android Studio and Arduino Programming. He has designed multiple robots and given lecture to engi…

Featured in Logiqids Blog

Page updated

Google Sites

Report abuse