AI

4141 readers

1 users here now

Artificial intelligence (AI) is intelligence demonstrated by machines, unlike the natural intelligence displayed by humans and animals, which involves consciousness and emotionality. The distinction between the former and the latter categories is often revealed by the acronym chosen.

founded 3 years ago

How can I create an AI model from this dataset? (raw.githubusercontent.com)

submitted 5 months ago by [email protected] to c/[email protected]

11 comments fedilink hide all child comments

Hello,

I want to create an AI model to learn about AI/ML. so I have scraped some data from Threads and Instagram.now I am wondering how can I use this dataset to make an AI model or do something useful with it? (BTW I don't know anything about AI/ML. I have done internship as Data Analyst so I know a little bit about Linear regression etc. but don't know anything advance.)

I am really curious to explore this space :)

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 7 points 5 months ago (1 children)

I would ignore the people who say you should deploy a model from someone else as that will teach you next to nothing about how this stuff works.

I would start with an older model and framework (e.g. scikitlearn) and go through all the processing, prediction, and evaluation steps using a model that's fairly simple to understand. Since you already know about linear regression, start with some of these linear models.

Then, and only then, would I worry about neural networks and deep learning, since the main difference is a non-linear activation function and a much more complicated set of weights (model parameters in the linear regression language).

Here is an example

Source: PhD in neural networks

[–] [email protected] 2 points 5 months ago* (last edited 5 months ago)

You're right. I read past the "I want to learn ML" and went straight to "do something useful with the data".

If the goal is to understand how modern LLMs work, it's also good to read up on RNNs and LSTMs. For this, 3Blue1Brown does an amazing job, and even posted an in-depth video about transformers. I'd watch that next, followed by implementing a simple transformer in PyTorch (perhaps using the existing blocks).

You could argue that it's important to design everything from scratch first, but it's easier to first go high level, see how the network behaves, and then attempt to implement it yourself based on the paper. It is up to OP how comfortable he is with the topic though 😁