Active Learning. The Secret of Training Models Without Labels.
Ғылым және технология
A large part of the success of supervised machine learning systems is the existence of large quantities of labeled data. Unfortunately, in many cases, creating these labels is difficult, expensive, and time-consuming.
An obvious solution is to use machine learning to aid in the creation of the labels, but this presents a chicken and egg problem: how do we build a model to create labels before labeling our data to train that model?
Active Learning is one solution. A semi-supervised learning technique to build better-performing machine learning models using fewer training labels.
Paper mentioned in the video:
Active Learning Literature Survey. burrsettles.com/pub/settles.a...
🔔 Subscribe for more stories: www.youtube.com/@underfitted?...
📚 My 3 favorite Machine Learning books:
• Deep Learning With Python, Second Edition - amzn.to/3xA3bVI
• Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow - amzn.to/3BOX3LP
• Machine Learning with PyTorch and Scikit-Learn - amzn.to/3f7dAC8
Twitter: / svpino
Disclaimer: Some of the links included in this description are affiliate links where I'll earn a small commission if you purchase something. There's no cost to you.
Пікірлер: 47
Really helpful video, thanks. One small thing though, the sound effects on the title screens were a bit loud imo :)
@underfitted
Жыл бұрын
Noted! Thanks for the feedback!
@underfitted
Жыл бұрын
GOOD ONE!
@emeebritto
25 күн бұрын
yaa... >.
Nice video! You can also use a similar approach to compare models and stay with the one that performs best. Here is how: A few years ago I was collecting data in the chemistry lab in order to fit some models. Each experiment took 1 day to complete, so I started with a simple factorial design, fitted all models to the initial data set, and then predicted the point of maximum divergence between all models. That point was used as the next experiment and models we refitted thereafter. This procedure was repeated several times. Computing uncertainty in your predictions is similar, but only with one model.
@underfitted
Жыл бұрын
Thanks for sharing!
Nice video! Could you also explain about semi-supervised learning? There are not many videos that clearly explain about the progress so far in semi-supervised learning, even though the topic become more popular nowadays
Excellent Video. This channel is going to be huge soon
Loved the Idea of smart labelling. very cool
This is lit 🔥. Love this practical approach to Machine learning. Keep doing the amazing work 👏👏
@underfitted
Жыл бұрын
Thanks! Much more coming!
Another nice video! Learned a new concept - *Active Learning*
@underfitted
Жыл бұрын
Glad to hear that!
Thanks! This was exactly what I needed at the moment! (:
Great content! Thank you :)
Love it, world class content! Also agree. A thought: Why not start with few shot or zero shot learning before active learning?
@underfitted
Жыл бұрын
If you have a model capable of zero-shot, absolutely!
This method to me seems a little bit like boosting. I might be wrong though, but boosting is what came to my mind after watching the video.
Excellent Information 👍👍
@underfitted
Жыл бұрын
Glad it was helpful!
Great explanation, thanks! Do you have some example of labeling services providing this approach?. greetings !
A Very good video!
Great content!
@underfitted
Жыл бұрын
Thanks!
Super insightfull, I`m using this ideas right now!
@123arskas
Жыл бұрын
If you've made it public (for smaller scale projects) please give the link to its repo. Thank you
@underfitted
Жыл бұрын
Wonderful!
I love your videos, nice and extremely informative! Just a quick comment: is it possible not to have those " bommmm!" soun?(: It make impossible to listen your videos in a car or with headphone. Thank you!
@underfitted
Жыл бұрын
Thinks, Erdi! Yes, if you watch my last few videos, I’ve improved the audio, including removing that particular sound 😏
dynamic! Liked it more!
@underfitted
Жыл бұрын
Cool, thanks!
Hi, Santiago! Love your content! Could you please make a video on how to start machine learning as a beginner with some programming experience. I've been doing web dev but want to transit into ML. I will appreciate your response 😊
@underfitted
Жыл бұрын
It's coming soon!
Lovely video Santiago! Quick question: How do we label the low confidence data that the model initially had a hard time predicting since we also didn't know what the label was in the first place. How do we know the label/class to use for that low confidence predicted data when we re-train ?
@underfitted
Жыл бұрын
We will start by labeling some of the data manually. The goal is to seed the process to start generating automatic labels.
I've some queries. There's no proper practical application of it is it? Since the paper talks about methods proposed along with practical issues. Since your videos are straight to the point and you try to keep it simple, just wanna know if you've found practical implementation of it in Python etc. Do give a link to it in the description. Thank you
@underfitted
Жыл бұрын
Yeah, I've personally used Active Learning multiple times. It's a very practical way to decide how to label a dataset.
Very interesting
@underfitted
Жыл бұрын
Glad you think so!
1:03 - We need to Build a Model to Label the data we need, to Build a Model 🤯
@underfitted
Жыл бұрын
Yup :)
Hi, maybe a silly question but how you calculate the confidence after step 2?
@underfitted
Жыл бұрын
Assuming you are using a classification model, for example, that will be the confidence (probability) returned by the model. More specifically, the softmax value corresponding to the highest predicted class.
@CarlosBCU
Жыл бұрын
@@underfitted many thanks for your answer! What if we are running a regression?
Wow.
@underfitted
Жыл бұрын
Wow indeed