A Fine Slice Of SQL Server
In this video, I show how we can integrate with the Azure AI Services Speech service, using two different methods to capture speech from the microphone via our Streamlit application and submit that to Azure OpenAI.
Check out the video and final set of code. There’s an intermediate set of code for detecting a single utterance. But I think the final product works out pretty well.
Comments closedBala Priya C shares some tips and techniques:
If you’re familiar with machine learning, you know that the training process allows the model to learn the optimal values for the parameters—or model coefficients—that characterize it. But machine learning models also have a set of hyperparameters whose values you should specify when training the model. So how do you find the optimal values for these hyperparameters?
You can use hyperparameter tuning to find the best values for the hyperparameters. By systematically adjusting hyperparameters, you can optimize your models to achieve the best possible results.
This tutorial provides practical tips for effective hyperparameter tuning—starting from building a baseline model to using advanced techniques like Bayesian optimization. Whether you’re new to hyperparameter tuning or looking to refine your approach, these tips will help you build better machine learning models. Let’s get started.
Read on for those techniques. Incidentally, one of my “Old man yells at clouds” takes is that I dislike the existence of hyperparameters and consider them a modeling failure, essentially telling the implementer to do part of the researcher’s work. Knowing that they are necessary to work with for so many algorithms, there’s nothing to do but learn how to work with them effectively, but there’s a feel of outsourcing the hard work to users that I don’t like about the process. For that reason, I have extra respect for algorithms that neither need nor offer hyperparameters.
Comments closedAbid Ali Awan gives us a primer on TPOT:
AutoML is a tool designed for both technical and non-technical experts. It simplifies the process of training machine learning models. All you have to do is provide it with the dataset, and in return, it will provide you with the best-performing model for your use case. You don’t have to code for long hours or experiment with various techniques; it will do everything on its own for you.
In this tutorial, we will learn about AutoML and TPOT, a Python AutoML tool for building machine learning pipelines. We will also learn to build a machine learning classifier, save the model, and use it for model inference.
Click through to see an example of how to use the library.
Comments closedColin Gillespie introduces an R package for MLOps:
Most R users are familiar with the classic workflow popularised by R for Data Science. Data scientists begin by importing and cleaning the data, then iteratively transform, model, and visualise it. Visualisation drives the modeling process, which in turn prompts new visualisations, and periodically, they summarise their work and report results.
Click through for a demonstration of how to create and deploy a model using vetiver.
Comments closedIn this video, I take a look at an alternative to bootstrap aggregation & random forest: boosting. We cover a brief history of boosting and see how it works in action with XGBoost and LightGBM.
This is probably the video with the single largest number of links in my show notes. It’s also one of the shortest in the series; it’s funny how things work out sometimes.
Comments closedMicrosoft has released a new learning path yesterday, Build AI Apps with Azure Database for PostgreSQL. I had the good fortune to write two of these modules:
Click through for direct links for the two modules. The way we wrote these, you can do the modules in any order and they’re self-contained, so you can pick and choose which ones you’d like to do.
Comments closedThomas Sobolik and Leopold Boudard talk model drift:
Regardless of how much effort teams put into developing, training, and evaluating ML models before they deploy, their functionality inevitably degrades over time due to several factors. Unlike with conventional applications, even subtle trends in the production environment a model operates in can radically alter its behavior. This is especially true of more advanced models that use deep learning and other non-deterministic techniques. It’s not enough to track the health and throughput of your deployed ML service alone. In order to maintain the accuracy and effectiveness of your model, you need to continuously evaluate its performance and identify regressions so that you can retrain, fine-tune, and redeploy at an optimal cadence.
In this post, we’ll discuss key metrics and strategies for monitoring the functional performance of your ML models in production […]
Click through for the article. There’s a Datadog pitch at the end, but the info is useful regardless of which tool you’re using for monitoring.
Comments closedSiliang Jiao, et al, talk architecture:
Feature engineering is the process of using domain knowledge to extract features (characteristics, properties, attributes) from raw data. The extracted features are used for training the models that can predict values for relevant business scenarios. A feature engineering system provides the tools, processes, and techniques used to perform feature engineering consistently and efficiently.
This article elaborates on how to build a feature engineering system based on Azure Machine Learning managed feature store and Microsoft Fabric.
Click through to see how the pieces fit together.
Comments closedSteven Sanderson builds a plot:
In the realm of machine learning, visualizing model predictions is essential for understanding the performance and behavior of our algorithms. When it comes to regression tasks, plotting predictions alongside actual values provides valuable insights into how well our model is capturing the underlying patterns in the data. With the
plot_regression_predictions()function in tidyAML, this process becomes seamless and informative.
Read on to see how the function works and the kind of result you can expect from it.
Comments closedSteven Sanderson has been busy. First up, a post on tidyAML updates:
One of the standout features in this release is the addition of
extract_regression_residuals(). This function empowers users to delve deeper into regression models, providing a valuable tool for analyzing and understanding residuals. Whether you’re fine-tuning your models or gaining insights into data patterns, this enhancement adds a crucial layer to your analytical arsenal.
Then, Steven goes into detail on .drap_na:
In the newest release of tidyAML there has been an addition of a new parameter to the functions
fast_classification()andfast_regression(). The parameter is.drop_naand it is a logical value that defaults toTRUE. This parameter is used to determine if the function should drop rows with missing values from the output if a model cannot be built for some reason. Let’s take a look at the function and it’s arguments.
After that, we get to see an updated function:
In response to user feedback, we’ve enhanced the
internal_make_wflw_predictions()function to provide a comprehensive set of predictions. Now, when you make a call to this function, it includes:
- The Actual Data: This is the real-world data that your model aims to predict. Having access to this information helps you assess how well your model is performing on unseen instances.
- Training Predictions: Predictions made on the training dataset. This is essential for understanding how well your model generalizes to the data it was trained on.
- Testing Predictions: Predictions made on the testing dataset. This is crucial for evaluating the model’s performance on data it hasn’t seen during the training phase.
You can also check out the package’s GitHub repository and see more.
Comments closed