#31DaysofML

 It’s New Year... & are you ready to learn something new? #31DaysofML is a mini-series started by Priyanka Vergadia, where she’ll be creating & sharing 31 posts on #MachineLearning.  Follow her to not miss any post.

🔊 So excited to share this with you on day 30 #31DaysofML Built a sound classification model for these sounds 🎸Guitar 🐦 Bird 👏 Clap Also deployed the model on Cloud Run! Want to try it yourself? code 👉 #MachineLearning #NoCode #GoogleCloud

🏹 Let's go Day 1 of #31DaysofML 💡What is #MachineLearning? 💡 ML = Using data to answer questions! 📌 Using data = Training 📌 Answer questions = Predictions Let's keep going... 🧵👇

Day 15 of #31DaysofML by @pvergadia Here are the basic #MachineLearning terms you will come across as you start your #ML journey ✅ Label ✅ Example ✅ Feature ✅ Model #ai #ml #datascience

Day 12 of #31DaysofML I played with Teachable Machine today and created a #nocode classification model in less than 5 mins! It's a web-based tool making #machinelearning models fast, easy, and accessible to everyone. See how I created a yoga pose classification model 🧵👇

👋 It’s New Year... & I’m ready for a new project 😎 I’m starting a mini-series called #31DaysofML, where I’ll be creating & sharing 31 posts on #MachineLearning. Let me know below the topics I should cover👇 Follow & click on the bell 🔔 on my profile to not miss any tweet.

Day 9 of #31DaysofML 💁‍♀️ I thought today I would share a tip that has helped me in my #MachineLearning journey 💡The best way to learn ML is to pick a problem that you feel excited about & let it guide your learning path. Don't worry about the terms or tools, it's all secondary

@GCPPodcast Next, I started digging into the Media Translation API which would translate audio & video data. My point is: 📌 You don't always need to create a model 📌 Save yourself time & resources by using the models that already exist (if they server your purpose) #31DaysofML (3/5)

@GCPPodcast Media translation API served my purpose. It was: 🔹 Easy to setup 🔹 Provided real-time translations 🔹 Accuracy was high 🔹 I did not have to use Speech-to-Text & Translation models separately Read more 👉 #31DaysofML (4/5)

Since it is Day 10 of #31DaysofML it's perfect to discuss 1️⃣0️⃣ things that can go wrong with #MachineLearning Projects and what you can do about it! I watched this amazing presentation by @kweinmeister that sums it all up A 🧵

@kweinmeister 3️⃣ Model training can take a long time 👉 When your team is trying to rapidly iterate on new ideas and techniques, training time can slow down projects and get in the way of innovation. 👉 Use GPU's, TPUs to speed up training 👉 Use serverless training methods #31DaysofML

@kweinmeister 4️⃣ You have an imbalanced dataset ❓ How can you balance accuracy across each class? 👉 Weighting each class 👉 Oversampling and undersampling 👉 Generating synthetic data Here's a tutorial to checkout #31DaysofML

@SRobTweets Kubeflow - OS project for deploying ML workloads on #Kubernetes 🔹 Helps configure a multi-step ML pipeline including pre-processing data, training & serving the model 🔹 Run it on-premise or on any cloud 🔹 You’ll still need to configure where it’s managed #31DaysofML 5/10

@SRobTweets AI Platform - managed service for all custom model needs 🔹 Includes tools for training & serving models, hosted notebooks, a data labeling service & more 🔹 Eg: take notebook code running on-premise with Kubeflow, and run it on GCP with AI Platform Notebooks #31DaysofML 6/10

Day 15 of #31DaysofML by @pvergadia Here are the basic #MachineLearning terms you will come across as you start your #ML journey ✅ Label ✅ Example ✅ Feature ✅ Model #ai #ml #datascience

👋 Day 3 of #31DaysofML by @pvergadia There are different types of learning models. These 4 are the most common that you usually come across. 📌 Supervised 📌 Unsupervised 📌 Semi-supervised 📌 Reinforcement #MachineLearning

Day 16 of #31DaysofML Here are some use cases of computer vision ✅ Industrial inspection 👗 Product search 📃 Document classification 🖼 Image search Checkout the architectures to implement using Vision API with #NoCode #MachineLearning

Day 21 #31DaysofML Pandas - most powerful tool in #datascience for data wrangling. Today I am focusing on how to get started with Pandas & manipulate our data for #MachineLearning. 🐼 Where does the term come from? Panel Data - a common term for multi-dimentional data A 🧵 👇

Pandas loads the data into a DataFrame. Which can be thought of as a table. Common DataFrame functions: 👉 DataFrame.head() - returns a quick glimpse of the data #31DaysofML 3/7

Another DataFrame function 👉 DataFrame.describe(include=''all") 🔹 Displays a table of statistics about the DataFrame 🔹 Useful for sanity checking the dataset 🔹 Seeing if the data distribution looks reasonable 🔹 Checking if the properties are as expected #31DaysofML 4/7

🏹 Let's go Day 1 of #31DaysofML 💡 What is #MachineLearning?💡 ML = Using data to answer questions! 📌 Using data = Training 📌 Answer questions = Predictions Learn more in this thread... #ml #ai #datascience #data #artificialintelligence

@SRobTweets Deep Learning VMs provide managed, click-to-deploy VMs for processing data & training the model 🔹 Popular ML frameworks pre-installed 🔹 Reduces the overhead of managing & allocating compute & storage required 🔹 But you figure out how you’ll serve those models #31DaysofML 4/10

New and Excited to learn #TensorFlow #MachineLearning Follow @pvergadia for #31DaysOfML #awesome #community ... #learning continues at #TFEverywhereIndia #TFEverywhere2021 @TFUGIndia @TFUGChandigarh @TensorFlow

👋 Day 12 of #31DaysofML by @pvergadia Explore Teachable Machine & create a #nocode classification model in less than 5 mins! Try it yourself 👉

 It’s New Year... & are you ready to learn something new? #31DaysofML is a mini-series started by Priyanka Vergadia, where she’ll be creating & sharing 31 posts on #MachineLearning.  Follow her to not miss any post.