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 🧵👇
teachablemachine.withgoogle.com
#nocode #31DaysofML
It's a web-based tool making #machinelearning models fast, easy, and accessible to everyone.
See how I did it 🧵👇
teachablemachine.withgoogle.com
#nocode #31DaysofML
How do I use it?
📌Gather data (upload it)
📌Train model (in the web interface)
📌Export the model (use it in your app)
📌Gather data (upload it)
📌Train model (in the web interface)
📌Export the model (use it in your app)
What can I use to teach it?
📌Images
📌Sounds
📌Poses
We can use files or capture examples live through webcam/microphone.
📌Images
📌Sounds
📌Poses
We can use files or capture examples live through webcam/microphone.
Day 14 #31DaysofML
🤔 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?
🧵 👇
🤔 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?
🧵 👇
@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 👉
#31DaysofML 2/10
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 👉
#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
#31DaysofML 3/10
Day 13 #31DaysofML
⚖️ How to deal with imbalanced datasets?⚖️
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?
🧵 👇
⚖️ How to deal with imbalanced datasets?⚖️
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?
🧵 👇
🐱🐱🐱🐱🐱🐱🐱🐱🐱🐶 (90:10)
💳 💳 💳 💳 💳 💳 💳 💳 💳 ⚠️ (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 👇 techniques can help
#31DaysofML 2/7
💳 💳 💳 💳 💳 💳 💳 💳 💳 ⚠️ (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 👇 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:
⚖️ Downsampling
⚖️ Upsampling
⚖️ Weighted classes
#31DaysofML 3/7
⚖️ Downsampling
⚖️ Upsampling
⚖️ Weighted classes
#31DaysofML 3/7
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 🧵👇
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 🧵👇
🤔 How to use Teachable Machines?
📌Gather data (upload it or use webcam/microphone)
📌Train model (in the web interface)
📌Export the model (use it in your app)
🤔 What type of data can I use to train the model?
🖼 Images
🔊 Sounds
🧘♀️ Poses
#31DaysofML
📌Gather data (upload it or use webcam/microphone)
📌Train model (in the web interface)
📌Export the model (use it in your app)
🤔 What type of data can I use to train the model?
🖼 Images
🔊 Sounds
🧘♀️ Poses
#31DaysofML
Now, get out of your chair 🪑 and try out my yoga 🧘♀️ pose classification model with any of these poses:
📌 Goddess
📌 Warrior2
📌 Tree
📌 Downdog
Here is my model 👉 teachablemachine.withgoogle.com/models/vkzpnwt…
#31DaysofML
📌 Goddess
📌 Warrior2
📌 Tree
📌 Downdog
Here is my model 👉 teachablemachine.withgoogle.com/models/vkzpnwt…
#31DaysofML
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 🧵
I watched this amazing presentation by @kweinmeister that sums it all up
A 🧵
@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?
👉 Focus on a long-term mission with maximum impact
👉 Ensure that your problem is a good fit for ML
#31DaysofML
❓What's the goal of your ML model?
❓How do you assess if your model is "good" or "bad"?
❓What's your baseline?
👉 Focus on a long-term mission with maximum impact
👉 Ensure that your problem is a good fit for ML
#31DaysofML
@kweinmeister 2️⃣ Jumping into development without a prototype
👉 ML project is an iterative process
👉 Start with simple model & continue to refine it until you've reached your goal
👉 Quick prototype can tell a lot about hidden requirements, implementation challenges, scope, etc
#31DaysofML
👉 ML project is an iterative process
👉 Start with simple model & continue to refine it until you've reached your goal
👉 Quick prototype can tell a lot about hidden requirements, implementation challenges, scope, etc
#31DaysofML
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
💁♀️ 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
Here's an example. Few weeks ago I wanted to live translate an episode of @GCPPodcast. The first question I asked myself was:
🤔 Does any video/audio translation API already exist?
🔹 If so - I would give that a try
🔹 If not, I would create it from scratch
#31DaysofML (2/5)
🤔 Does any video/audio translation API already exist?
🔹 If so - I would give that a try
🔹 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:
📌 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)
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)
Day 8 of #31DaysofML
📖 Learning Rate 📖 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 🧵
📖 Learning Rate 📖 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 🧵
👉 Smaller the learning rate the longer it will take to find the lowest loss value
👉 Large learning rate could overshoot the minimum
👉 You the learning rate to be just right (Goldilock's learning rate) to get the convergence value efficiently
#31DaysofML 2/3
👉 Large learning rate could overshoot the minimum
👉 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
#31DaysofML 3/3
Day 7 of #31DaysofML
⬇️ Reducing Loss ⬇️
An iterative process of choosing model parameters that minimize loss
👉 Loss function is how we compute loss
👉 Loss function curve is convex for linear regression
A 🧵 👇
⬇️ Reducing Loss ⬇️
An iterative process of choosing model parameters that minimize loss
👉 Loss function is how we compute loss
👉 Loss function curve is convex for linear regression
A 🧵 👇
Calculating loss for every value of W isn't efficient: most common way is called gradient descent
👉 Start with any value of w, b (weights & biases)
👉 Keep going until overall loss stops changing or changes slowly
👉 That point is called convergence
#31DaysofML 2/4
👉 Start with any value of w, b (weights & biases)
👉 Keep going until overall loss stops changing or changes slowly
👉 That point is called convergence
#31DaysofML 2/4
As you probably already guessed, gradient is a vector with:
👉 Direction
👉 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
👉 Direction
👉 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
Day 6 of #31DaysofML
🕹 Training & Loss 🕹
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 🧵
🕹 Training & Loss 🕹
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
📌 Loss indicates how bad model's prediction was on an example
📌 Loss = 0 if the model's prediction is perfect otherwise it's greater.
📌 Goal of training is to find weights & biases that have low loss, on average, across dataset
#31DaysofML
📌 Loss indicates how bad model's prediction was on an example
📌 Loss = 0 if the model's prediction is perfect otherwise it's greater.
📌 Goal of training is to find weights & biases that have low loss, on average, across dataset
#31DaysofML
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
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
👋 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
🔸Model input = 🍏🥦🧅🍓🥞🥖🍚
🔸Model output = cluster of vegetarian/vegan
A 🧵
⚡️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
🔸Model input = 🍏🥦🧅🍓🥞🥖🍚
🔸Model output = cluster of vegetarian/vegan
A 🧵
2/8
When is unsupervised learning used?
🔸 On large datasets where annotating (labeling) data is costly
🔸 When we don't know how many classes might exist in the data
🔸 Cluster the data to apply classification on the individual clusters
#31DaysofML
When is unsupervised learning used?
🔸 On large datasets where annotating (labeling) data is costly
🔸 When we don't know how many classes might exist in the data
🔸 Cluster the data to apply classification on the individual clusters
#31DaysofML
@quaesita has demystified unsupervised learning here 👉 bit.ly/quaesita_unsup…
🏹 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... 🧵👇
💡What is #MachineLearning? 💡
ML = Using data to answer questions!
📌 Using data = Training
📌 Answer questions = Predictions
Let's keep going... 🧵👇
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 👉bit.ly/3j3j2ne
#31DaysofML
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 👉bit.ly/3j3j2ne
#31DaysofML
@yufengg 1️⃣ Collect Data
📌Quantity & quality of your data dictate how accurate our model is
📌The outcome of this step is usually a table with some values (features)
📌 If you want to use pre-collected data - get it from sources such as Kaggle or BigQuery Public Datasets
#31DaysofML
📌Quantity & quality of your data dictate how accurate our model is
📌The outcome of this step is usually a table with some values (features)
📌 If you want to use pre-collected data - get it from sources such as Kaggle or BigQuery Public Datasets
#31DaysofML
