Discover and read the best of Twitter Threads about #31daysofml

Most recents (11)

Experimented 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 did it πŸ§΅πŸ‘‡

teachablemachine.withgoogle.com

#nocode #31DaysofML
How do I use it?

πŸ“ŒGather data (upload it)
πŸ“ŒTrain model (in the web interface)
πŸ“ŒExport the model (use it in your app) Image
What can I use to teach it?

πŸ“ŒImages
πŸ“ŒSounds
πŸ“ŒPoses

We can use files or capture examples live through webcam/microphone. Image
Read 5 tweets
Day 14 #31DaysofML

πŸ€” How to pick the right #GoogleCloud #MachineLearning tool for your application?

Answer these questions
❓ What's your teams ML expertise?
❓ How much control/abstraction do you need?
❓ Would you like to handle the infrastructure components?

🧡 πŸ‘‡
@SRobTweets created this pyramid to explain the idea.
As you move up the pyramid, less ML expertise is required, and you also don’t need to worry as much about the infrastructure behind your model.

To lear more watch this video πŸ‘‰

#31DaysofML 2/10
@SRobTweets If you’re using Open source ML frameworks (#TensorFlow) to build the models, you get the flexibility of moving your workloads across different development & deployment environments. But, you need to manage all the infrastructure yourself for training & serving

#31DaysofML 3/10
Read 10 tweets
Day 13 #31DaysofML

βš–οΈ How to deal with imbalanced datasets?βš–οΈ
Most real-world datasets are not perfectly balanced. If 90% of your dataset belongs to one class, & only 10% to the other, how can you prevent your model from predicting the majority class 90% of the time?

🧡 πŸ‘‡
🐱🐱🐱🐱🐱🐱🐱🐱🐱🐢 (90:10)
πŸ’³ πŸ’³ πŸ’³ πŸ’³ πŸ’³ πŸ’³ πŸ’³ πŸ’³ πŸ’³ ⚠️ (90:10)
There can be many reasons for imbalanced data. First step is to see if it's possible to collect more data. If you're working with all the data that's available, these πŸ‘‡ techniques can help

#31DaysofML 2/7
Here are 3 techniques for addressing data imbalance. You can use just one of these or all of them together:
βš–οΈ Downsampling
βš–οΈ Upsampling
βš–οΈ Weighted classes

#31DaysofML 3/7
Read 7 tweets
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 πŸ§΅πŸ‘‡
πŸ€” How to use Teachable Machines?
πŸ“ŒGather data (upload it or use webcam/microphone)
πŸ“ŒTrain model (in the web interface)
πŸ“ŒExport the model (use it in your app)

πŸ€” What type of data can I use to train the model?
πŸ–Ό Images
πŸ”Š Sounds
πŸ§˜β€β™€οΈ Poses

#31DaysofML Image
Now, get out of your chair πŸͺ‘ and try out my yoga πŸ§˜β€β™€οΈ pose classification model with any of these poses:
πŸ“Œ Goddess
πŸ“Œ Warrior2
πŸ“Œ Tree
πŸ“Œ Downdog

Here is my model πŸ‘‰ teachablemachine.withgoogle.com/models/vkzpnwt…
#31DaysofML
Read 3 tweets
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 🧡 Image
@kweinmeister 1️⃣ You aren't solving the right problem
❓What's the goal of your ML model?
❓How do you assess if your model is "good" or "bad"?
❓What's your baseline?
πŸ‘‰ Focus on a long-term mission with maximum impact
πŸ‘‰ Ensure that your problem is a good fit for ML

#31DaysofML
@kweinmeister 2️⃣ Jumping into development without a prototype
πŸ‘‰ ML project is an iterative process
πŸ‘‰ Start with simple model & continue to refine it until you've reached your goal
πŸ‘‰ Quick prototype can tell a lot about hidden requirements, implementation challenges, scope, etc

#31DaysofML
Read 11 tweets
Day 9 of #31DaysofML

πŸ’β€β™€οΈ I thought today I would share a tip that has helped me in my #MachineLearning journey
πŸ’‘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
Here's an example. Few weeks ago I wanted to live translate an episode of @GCPPodcast. The first question I asked myself was:
πŸ€” Does any video/audio translation API already exist?
πŸ”Ή If so - I would give that a try
πŸ”Ή If not, I would create it from scratch

#31DaysofML (2/5)
@GCPPodcast Next, I started digging into the Media Translation API which would translate audio & video data.
My point is:
πŸ“Œ You don't always need to create a model
πŸ“Œ Save yourself time & resources by using the models that already exist (if they server your purpose)

#31DaysofML (3/5)
Read 5 tweets
Day 8 of #31DaysofML

πŸ“– Learning Rate πŸ“– Also known as Step size
It's a scalar that is multiplied with gradient vector (which has the direction & magnitude) to provide the next value on the loss curve

A 🧡 Image
πŸ‘‰ Smaller the learning rate the longer it will take to find the lowest loss value
πŸ‘‰ Large learning rate could overshoot the minimum
πŸ‘‰ You the learning rate to be just right (Goldilock's learning rate) to get the convergence value efficiently

#31DaysofML 2/3
Learning rate is one of the "Hyperparameters" that we tweak in machine learning algorithms. This is to tune the learning rate to efficiently get to the lowest loss value. There are more hyperparameters which we will get to later...

#31DaysofML 3/3 Image
Read 3 tweets
Day 7 of #31DaysofML

⬇️ Reducing Loss ⬇️
An iterative process of choosing model parameters that minimize loss
πŸ‘‰ Loss function is how we compute loss
πŸ‘‰ Loss function curve is convex for linear regression

A 🧡 πŸ‘‡ Image
Calculating loss for every value of W isn't efficient: most common way is called gradient descent
πŸ‘‰ Start with any value of w, b (weights & biases)
πŸ‘‰ Keep going until overall loss stops changing or changes slowly
πŸ‘‰ That point is called convergence

#31DaysofML 2/4 Image
As you probably already guessed, gradient is a vector with:
πŸ‘‰ Direction
πŸ‘‰ Magnitude
Gradient descent algorithms multiply the gradient by a scalar known as the learning rate (or step size) to determine the next point.

#31DaysofML 3/4
Read 4 tweets
Day 6 of #31DaysofML

πŸ•Ή Training & Loss πŸ•Ή

In supervised learning training a model means learning good values for weights & bias from labeled examples. In doing so it attempts to find a model that minimizes loss. Process is called empirical risk minimization

A 🧡
2/4
πŸ“Œ Loss indicates how bad model's prediction was on an example
πŸ“Œ Loss = 0 if the model's prediction is perfect otherwise it's greater.
πŸ“Œ Goal of training is to find weights & biases that have low loss, on average, across dataset

#31DaysofML Image
3/4
Squared loss or L2 loss is a popular Loss function that aggregates the individual losses

L2 loss for a single example = (observation - prediction)^2

#31DaysofML
Read 5 tweets
πŸ‘‹ Day 5 of #31DaysofML

⚑️Unsupervised learning ⚑️
Input data is unlabeled & the program learns to recognize the inherent patterns in the input data

Eg: Data across few people's eating habits
πŸ”ΈModel input = 🍏πŸ₯¦πŸ§…πŸ“πŸ₯žπŸ₯–πŸš
πŸ”ΈModel output = cluster of vegetarian/vegan

A 🧡
2/8
When is unsupervised learning used?
πŸ”Έ On large datasets where annotating (labeling) data is costly
πŸ”Έ When we don't know how many classes might exist in the data
πŸ”Έ Cluster the data to apply classification on the individual clusters

#31DaysofML
@quaesita has demystified unsupervised learning here πŸ‘‰ bit.ly/quaesita_unsup…
Read 10 tweets
🏹 Let's go Day 1 of #31DaysofML

πŸ’‘What is #MachineLearning? πŸ’‘

ML = Using data to answer questions!
πŸ“Œ Using data = Training
πŸ“Œ Answer questions = Predictions

Let's keep going... πŸ§΅πŸ‘‡
2/4 What are the 7 steps in Machine Learning?

1️⃣ Collect Data
2️⃣ Prepare Data
3️⃣ Choose a Model
4️⃣ Train the Model
5️⃣ Evaluate the Model
6️⃣ Parameter Tuning
7️⃣ Make Predictions

For more @yufengg amazing video πŸ‘‰bit.ly/3j3j2ne

#31DaysofML
@yufengg 1️⃣ Collect Data

πŸ“ŒQuantity & quality of your data dictate how accurate our model is
πŸ“ŒThe outcome of this step is usually a table with some values (features)
πŸ“Œ If you want to use pre-collected data - get it from sources such as Kaggle or BigQuery Public Datasets

#31DaysofML
Read 9 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!