I have recently started my first steps in causal inference and looking to practice further.
Is anyone aware of any good resource that provides examples of directed acyclic graphs and the appropriate regression models for each?
Related
I know there are quite many hands-on tutorials about deploying BERT or other models. But the problem is many of them are just shallow user cases which only modified a few parameters using apis from a certain libraries such as keras. I am a novice and I often find my still confused at the details and variational steps when deploying pre-trained language models on my projects.
Could anyone give a hint on what is a better roadmap for learning coding with pre-trained language models, including any resources, articles, or tutorials, etc.
I have read many articles on Medium. But most articles there seems only introduc the general concepts, rather than providing the real know-how when learning it.
I find these two courses very novice-friendly:
Hugging Face course
https://huggingface.co/course/chapter1/1
Deep Lizard "Deep Learning Fundamentals - Classic Edition"
https://deeplizard.com/learn/playlist/PLZbbT5o_s2xq7LwI2y8_QtvuXZedL6tQU
I want to make a AI gym Trainer app.the purpose of this app will be to correct the poses of the person performing the exercise, he/she will perform the exercise in front of the camera and the model will then evaluate it and provide guidance for correcting it. I have one issue that i am not fully aware what the Deep Learning Field has to offer.
My questions:
Are models capable of comparing the input pose with what it has learned through the dataset and provide feedback?
Can a model show the pose for correcting the user through any visual means, like by showing the skeleton structure to user performing that particular exercise?
I need to find a deep learning based prediction model, where can I find it?
You can use Pytorch and Tensorflow pretrained models.
https://pytorch.org/docs/stable/torchvision/models.html
They can be automatically downloaded. There are some sample codes, that you can try:
https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html#sphx-glr-beginner-blitz-cifar10-tutorial-py
If you are interested in deep learning, I suggest you review the basics of it in cs231n stanford. Your question is a bit odd, because you first need to define your task specifically. Prediction is not a good description. You could look for models for classification, segmentation, object detection, sequence2sequence(like translation), and so on...
Then you need to know how to search through projects on github, and then you need to know python (in most cases), and then use a pretrained model or use your own dataset to train or fine-tune the model for that task. Then you could pray that you have found a good model for your task, after that you need to validate the results on a test set. However, implementation of a model for real-life scenarios is another thing that you need to consider many other things, and you usually need some online-learning strategy, like Federated Learning. I hope that I could help you.
Deep Reinforcement Learning can be very useful in applying it to real-world problems which have highly dynamic nature. Few examples can be listed as is finance, healthcare etc. But when it comes to these kinds of problems it is hard to have a simulated environment. So what are the possible things to do?
Let me first comment a couple concepts trying to give you future research directions according to your comments:
Probably the term "forecast" is not suitable to describe the kind of problems solved by Reinforcement Learning. In some sense, RL needs to do an internal forecast process to choose the best actions in the long term. But the problem solved is an agent choosing actions in an environment. So, if your problem is a forecast problem, maybe other techniques are more suitable than RL.
Between tabular methods and deep Q-learning there exist many other methods that maybe are more suitable to your problem. They are probably less powerful but easy to use (more stable, less parameter tuning, etc.) You can combine Q-learning with other function approximators (simpler than a deep neural network). In general, the best choice is the simplest one able to solve the problem.
I don't know how to simulate the problem of human activities with first-person vision. In fact, I don't fully understand the problem setup.
And regarding to the original question of applying RL without accessing a simulated environment, as I previously said in the comments, if you have enough data, you could probably apply an RL algorithm. I'm assuming that you can store data from your environment but you can not easily interact with it. This is typical, for example, in medical domains where there exist many data about [patient status, treatment, next patient status], but you can not interact with patients by applying random treatments. In this situation, there are some facts to take into account:
RL methods generally consume a very large quantity of data. This is specially true when combined with deep nets. How much data it is necessary depends totally of the problem, but be ready to store millions of tuples [state, action, next state] if your environment is complex.
The stored tuples should be collected with a policy which contains some exploratory actions. RL algorithm will try to find the best possible actions among the ones contained in the data. If the agent can interact with the environment, it should choose exploratory actions to find the best one. Similarly, if the agent cannot interact and instead the data is gathered in advance, this data also should contain exploratory actions. The papers Neural Fitted Q Iteration - First Experiences
with a Data Efficient Neural Reinforcement
Learning Method and Tree-Based Batch Mode Reinforcement Learning could be helpful to understand these concepts.
I need to query AutoCAD models to extract structures and connections (e.g., power, data) between them, for storage in a database. I know from experience and research that handling native AutoCAD .dwg is problematic due to the proprietary nature of the format. I see that AutoCAD features a .NET API, but still the problem looks daunting since I have essentially no knowledge a priori of the content of the models. The problem seems like a PhD thesis, as my initial googling hasn't yielded much in the way of tools support or examples.
Are there tools / libraries / examples available to help make AutoCAD extraction feasible in a compressed schedule on a small budget?
I have essentially no knowledge a
priori of the content of the models.
The library is not your problem. Your problem is how the data is modelled, or isn't modelled. You may need to cater for a range of things from attributed blocks to seemingly-unrelated, random bits of text scattered in the proximity of the items in question. If there is no standard for the way this information is stored in the drawing then there is no standard way of machine-reading it. It will probably take longer than a PHD thesis to extract it. You cannot guarantee any sort of comprehensive accuracy either.
AutoCAD (full version, not LT) has Data Extraction routine to extract blocks and attributes from a drawing. If that is how the data is presented then you might be in luck.
It might be cheaper and quicker to hire a team of Muppets to go through the drawings and type the data into something like Excel. You'd be (un)surprised how widespread this sort of practise is, even these days.
As for an inexpensive library, try the Open Design alliance, as mentioned in other AutoCAD questions on this site.