Here is a great summary or glossary doc about LLM by Aman Chadha. This long doc provides a summary of some of the main concepts related to LLM. This includes topics such as:
✅ Embeddings
✅ Vector database
✅ Prompt engineering
✅ Token
✅ RAG
✅ LLM performance evaluation
✅ Review main LLMs
Please boost for reach if this kind of stuff interests you. Will post more on this later.
Once upon a time, there was a cool emulator frontend called Retroarch. This emulator wasn't accessible until I and a few other gamers went to them and asked about adding accessibility. An amazing person known as BarryR made it happen. Now, if you turn on accessibility mode in settings, or pass the "--accessibility" (or something like that) flag on the command line, you get spoken menus, including the emulator's pause menu, good for saving states and such. Then, using PIL and other image processing Python utilities, running a server and hooking into Retroarch, the script allowed players to move around the map, battle, talk to NPC's, ETC. The only problem was, no one wanted to test it. The blind gaming community pretty much spoke, saying that we want new games. We want cool new, easy accessibility. So that's what we have no, follow the beacon or get sighted help in the case of diablo and such. It's sad, but meh. It's what we wanted I guess. No Zelda for us. So, this is about as far as he got:
To expand on what devinprater was saying: I am working on an accessibility pack/service for Final Fantasy 1 for the NES (this was what was shown in the latest RetroArch update). The idea is similar to how Pokemon Crystal access works, but it's using the RetroArch AI Service interface to do so.
Right now, the FF1 access service is mostly done, but I need more testers to try it out and give me feedback on how it's working. Right now, you can get up to the point where you get the ship, but there's no code to deal with how the ship moves, so that still needs to be done. Likewise with the airship later on.
The service works the latest version of RetroArch, on linux and mac, but not windows. This is due to how nvda reads out the text and until the next major update to nvda (which will have a feature to fix this), it'll have to wait. If you have those, I (or maybe devinprater) can help you set it up on mac/linux to test out. The package itself is available at: https://ztranslate.net/download/ff1_pac … zip?owner=
So, I get that old games are, well, old. I get that new games are really cool. And I know, I'm the biggest hypocrit of them all because I can't code and should be spending 24/7 learning to code so I can be the change I want to see in the world and all that FossShit. And honestly, I don't know how hard it was to make that project, I really don't. But if that can be done, I kinda have the feeling that modders that make Super Mario hacked ROMs, or decompile Super Mario 64, maybe could spend a bit of time on accessibility of these old games.
And here we come to a sad truth. Just because a community is small, does not mean accessibility will be prioritized. Just because a game studeo is huge, like Netherrealm Studeos, doesn't mean accessibility will be forgotten, either. I've gone to several different emulation communities. I asked for audio cues to be added into PPSSPP, and that's why they're in there now. Since the GUI can't be made accessible, I can still navigate it on mobile with a controller. I'm currently trying to get Provinence and Ignited made more accessible. I've kinda given up on Delta because that team has all the hype so is less likely to listen, at least that's kinda how I feel.
But seriously though, there aren't many activists among us. And there's just not much the few of us can do. But my dream, and I know how pathetic dreams are in this age of everyone looking down on everyone else, is that a blind person can enjoy and preserve in our own culture, what sighted people have been able to access for the last 20 years or so. Thousands of games, just sitting there ready to play. And I mean, this was like 4 years ago, with less blind programmers out there, less resources for ROM hacking and emulator scripting, and less devs. Now that emulation is on iOS, I seriously hope that this improves. I mean, imagine a blind person that uses their iPhone as their only computing device, being able to just download an emulator, already having scripts pre-installed and ready for a ROM, being able to just plop in Chrono Trigger and playing it like anyone else. That's my dream. Stupid, yes. But equal access has probably always seemed stupid before it's a thing.
And honestly, I wouldn't even start with the huge projects, like Zelda. I'd start with Mortal Kombat, Street Fighter, Soul Calibur, all that. Make the menus talk, read tutorials, move lists, pause screens, all that. I mean, I don't know how easy that would be, since their graphics are going to be different than Mario or Final Fantasy, but surely if we can do cheat codes that mess with memory ingame, we should be able to track the cursor in menus.
Version 1.7.1 of the NeuralForecast #Python library was released last month by Nixtla. The NeuralForecast library, as the name implies, provides a neural network framework for time series forecasting. 🧵👇🏼
(2/3) The release includes the support for the following new models:
✅ BiTCN - temporal convolutional networks forecasting model
✅ iTransformer - transformer-based forecasting model
✅ MLPMultivariate - an MLP model that supports multivariate tasks
In addition, the library now supports multi-node distributed training with Spark ✨ and Polars 🐻❄️ data frames 🚀
Wie wird #KI & #MachineLearning die Software-Entwicklung beeinflussen? Diskutiert mit bei der uphillconf 2024, die wir als Bronzesponsor unterstützen. Es sind nur noch wenige Workshop-Tickets verfügbar! https://www.uphillconf.com/
In yesterday’s post, we asked the basic question of what is machine learning. I hoped to illustrate the similarities and differences between artificial intelligence and machine learning. Lately, on this site, we have been spending a bit of time using Python and I wanted to take a moment today to look at a great library for machine learning in Python.
Scikit-learn is the go-to library for machine learning with an amazing ecosystem of plugins. It is open-source and supports supervised and unsupervised learning. It also provides various tools for model fitting, data preprocessing, model selection, model evaluation, and many other utilities. After you python3 -m venv EnvironmentName and source EnvironmentName/bin/activate, you can install it by running pip install scikit-learn. At that point, you can reference it in your code as sklearn.
The way that scikit-learn works is that you start with some data, you give it to a model, the model learns from it, and then you will be able to make predictions. The common notation is splitting up the data into a part called X (everything you are using to make a prediction) and another part called Y (the prediction you are interested in making). The X could be information about a house (square feet, number of bathrooms, etc) where Y is the house price, or X could be a patient’s health statistics where Y is whether or not they develop diabetes. The model then uses X to try to predict Y.
In the above code, we load the 20,640 records and 9 columns into the data variable and then we set the things that we are using to make a prediction to X and the prediction that we are interested in making to y. So, what are the feature (column) names for the data? If you print(data.feature_names), it will print them.
sklearn.model_selection
Once you have data, you can start working on creating a model. The model itself is nothing more than a Python object but the goal after you create it is to train it. You will want to split your data into a training set and a test set. Using <a href="https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html#sklearn.model_selection.train_test_split">train_test_split</a> in sklearn.model_selection, you can split it into 70% of the data for training the model and 30% of the data for testing the model (or whatever split you want).
In the above example, we are taking any X values except num_preg (the number of pregnancies) that have the value 0 and setting it to the mean. That makes it so that missing values don’t scew things when you go to train the model.
The neat thing about .fit() is that if you want to swap out the KNeighborsRegressor model with a new one, .fit() still works just the same. Let’s look at what it would look like using a linear regression model.
In the above code, we are predicting the value for y and then comparing it against the actual value of y. Using just the training data, it is predicting the values with a 75.23% level of accuracy.
So, what is next?
In a future post, I want to step through the whole process of picking a statement to test, adjusting the data, building and training a model, testing, adjusting the model, and making predictions. Let’s save that for another day, though.
Last week, we went over some basics of Artificial Intelligence (AI) using Ollama, Llama3, and some custom code. Artificial intelligence (AI) encompasses a broad range of technologies designed to enable machines to perform tasks that typically require human intelligence. These tasks include understanding spoken or written language, recognizing visual patterns, making decisions, and providing recommendations. Machine learning (ML) is a specialized subset of AI that focuses on developing systems that improve their performance over time without being explicitly programmed. Instead, ML algorithms analyze and learn from large datasets to identify patterns and make decisions based on these insights. This learning process allows ML models to make increasingly accurate predictions or decisions as they are exposed to more data.
A few months ago, I added Liner to the resource page of my website. It allows you to easily train an ML model so that you can do image, text, audio, or video classification, object detection, image segmentation, or pose classification. I created “Is this Joe or Not Joe?” using that tool. TensorFlow.js is running client-side with a model that is trained on a half dozen examples of photos that are Joe and a half dozen examples of photos that are not Joe. You can supply a photo and get a prediction if Joe is in the image or not. You can always retrain the existing model with more examples. That is an example of machine learning.
So, you can think of ML as a subset of AI and Deep Learning (DL) as a subset of ML.
Have any questions, comments, etc? Please feel free to drop a comment, below.