Artificial Intelligence on possi.be

A Guide to Model Selection Part I: Introduction to Time Series

Fri, 26 Dec 2025 00:00:00 +0000

Note: In this series, I intentionally avoid equations and code, because model selection is primarily a conceptual decision, not a programming one.

A Guide to Model Selection Part II: Memory vs No memory

Sun, 22 Feb 2026 00:00:00 +0000

Last time we talked about what a Time Series is. This time, we are going to talk about what happens inside the “brain” of the AI. Specifically, we need to look at whether a model understands the last state (what just happened) or if it doesn’t.

A Guide to Model Selection Part III: Forecasting vs Classification

Sun, 22 Feb 2026 00:00:00 +0000

Ever wonder what we actually do after the AI “reads” all those pictures? In the last part, we talked about Stateless and Stateful thinking. Now, we need to talk about the Intention; the reason why we are recognizing those pictures in the first place.

A Guide to Model Selection Part VI: Frequency, latency, and right-sized models

Sun, 22 Feb 2026 00:00:00 +0000

In this part, we will talk about the two most critical factors you must consider before putting your model to work: Frequency and Latency.

A Guide to Model Selection Part V: Why some models fail silently on Time-series data

Sun, 22 Feb 2026 00:00:00 +0000

In Part I, we introduced the fundamentals of Time-Series. After exploring other critical AI model factors in the intervening chapters, we are returning to the temporal world. In this installment, we analyze why models often fail silently on Time-Series data; specifically focusing on time-frame mismatches and the struggle of isolating signal from noise.

A Guide to Model Selection Part VI: When we shouldn't use AI model

Sun, 22 Feb 2026 00:00:00 +0000

This is the final installment in my series, and it might feel a bit counter-intuitive.

AI in Medicine Part I: Ready made AI for Medicine

Thu, 25 Dec 2025 00:00:00 +0000

The integration of Artificial Intelligence (AI) in medicine has evolved into two primary approaches: utilizing ready-made, pre-trained Machine Learning (ML) models or building custom systems trained on proprietary data. Understanding the distinctions between these two paths is essential for any healthcare organization looking to implement these technologies effectively.

AI in Medicine Part II: Things to consider before you implement ML

Sat, 20 Dec 2025 00:00:00 +0000

Before you begin, you must visualize the end: What exactly do you want your output to be? Is it a graph, a specific number, a trend line, bounding boxes on an image, or a specific frame in a video?

AI in Medicine Part III: Preparing, Cleaning, and Labeling Medical Data for AI Training

Sun, 21 Dec 2025 00:00:00 +0000

Continuing from our previous installment, we will focus on data preparation, which often proves to be the most critical and time-consuming phase of the project.

AI in Medicine Part IV: Building Medical AI: Input, Output, and Validation

Sun, 22 Feb 2026 00:00:00 +0000

In this section, we will explore how to plan input retrieval, including masking and pre-processing validation, before data enters the system. We will also discuss how to handle outputs and validate them against clinical expectations. What happens if an error occurs or the process deviates from the expected result?

AI in Medicine Part V: Training and Evaluation in medical AI

Mon, 22 Dec 2025 00:00:00 +0000

In this stage of the system lifecycle, our focus shifts from architectural design to proof of reliability. Training and evaluation are not simply about improving accuracy; they are about validating that a model can operate safely, efficiently, and predictably within a clinical environment.

AI in Medicine Part VI: Deploy AI in Clinical Environments

Tue, 23 Dec 2025 00:00:00 +0000

In this article, we will focus on these core topics:

AI in Medicine Part VII: Drift, Decay, and Prevention in Medical AI

Wed, 24 Dec 2025 00:00:00 +0000

In this article, we will explore two specific issues in AI modeling: Drift and Decay.

AI in Medicine Part VIII: Human factors and ethics in using medical AI

Wed, 24 Dec 2025 00:00:00 +0000

In previous articles, we have consistently emphasized that the human factor remains the most critical element in the application of medical AI. This installment focuses on optimizing AI usage and mitigating preventable errors. We will explore how the ethical application of these technologies can protect patients from harm and shield healthcare providers from complex legal issues.

AI in Medicine Part IX: End-of-Life Management for Medical AI

Thu, 25 Dec 2025 00:00:00 +0000

When a medical AI system has fulfilled its purpose, reached the end of a pilot project, lost its funding source, or been superseded by a newer model, ‘End-of-Life’ (EoL) management must be addressed. Proper decommissioning is not merely a technical shutdown; it is a critical requirement for clinical safety and regulatory compliance.