Why RAG Chatbots Struggle in Production
“Our RAG chatbot worked perfectly in the POC.But once we scaled to 50,000 documents… accuracy dropped to 60%.” If you’ve worked with enterprise RAG systems, you’ve probably heard this story.…
Measuring ROI for a GenAI Initiative in Healthcare
This blog explores how to measure ROI for Generative AI (GenAI) in healthcare. It outlines key performance indicators (KPIs) related to clinical outcomes, operational efficiency, finance, and patient experience. It…
Building a Regression MLP Using the Sequential API
Let’s switch to the California housing problem and tackle it using a regression neural network. For simplicity, we will use Scikit-Learn’s fetch_california_housing() function to load the data. This dataset is…
Logical Computations with Neurons | Deep learning
Warren McCulloch and Walter Pitts proposed a very simple model of the biological neuron, which later became known as an artificial neuron: it has one or more binary (on/off) inputs…
What is Stochastic Gradient Descent?
Stochastic Gradient Descent (SGD) is an optimization algorithm commonly used in machine learning for training models, particularly in large-scale and online learning settings. It is an iterative optimization algorithm that…
How to Extract Code from a Screenshot with 100% Accuracy?
Did you like an image containing code & take its screenshot? Now you want to copy the code from that screenshot, right? Panic not, because I’ve got you covered. In…
Quintile Analysis: Bringing it all togetherand making decisions
Introduction Quintile analysis is a statistical method used to divide a data set into five equal parts, each representing 20% of the total observations. This method is often used in…
Getting Started With Pandas | Part 1
Installation or Setup Detailed instructions on getting pandas set up or installed can be found here in the official documentation. Installing pandas with Anaconda Installing pandas and the rest of…
Selecting the Number of Clusters
With K-Means, you could use the inertia or the silhouette score to select the appropriate number of clusters, but with Gaussian mixtures, it is not possible to use these metrics…
Tokenization in NLP
Word Level Tokenzation Splitting text into individual words “the quick brown fox” -> BUT Character Level Tokenization Splitting text into individual characters “the quick brown fox” -> But N-GRAM MODELS…
Appending to DataFrame | Pandas
Appending a new row to DataFrame import pandas as pd df = pd.DataFrame(columns = ) Appending a row by a single column value: df.loc = 1 df Appending a row,…
What is Exploratory Data Analysis (EDA)?
Exploratory Data Analysis (EDA) is an essential step in any data science project. It involves investigating and analyzing datasets to understand their characteristics, identify patterns, detect outliers, and uncover relationships…
Anomaly Detection using Gaussian Mixtures
Introduction Anomaly detection (also called outlier detection) is the task of detecting instances that deviate strongly from the norm. These instances are of course called anomalies or outliers, while the…
A Journey From Biological to Artificial Neurons
Surprisingly, ANNs have been around for quite a while: they were first introduced back in 1943 by the neurophysiologist Warren McCulloch and the mathematician Walter Pitts. In their landmark paper,…
Bayesian Gaussian Mixture Models
Rather than manually searching for the optimal number of clusters, it is possible to use instead the BayesianGaussianMixture class which is capable of giving weights equal (or close) to zero…
Understanding DBSCAN Clustering Algorithm: Implementation in Python
Before we move on to Gaussian mixture models, let’s take a look at DBSCAN, another popular clustering algorithm that illustrates a very different approach based on local density estimation. This…
Using Clustering for Semi-Supervised Learning
Another use case for clustering is in semi-supervised learning, when we have plenty of unlabeled instances and very few labeled instances. Let’s train a logistic regression model on a sample…
Using clustering for image segmentation
Image segmentation is the task of partitioning an image into multiple segments. In semantic segmentation, all pixels that are part of the same object type get assigned to the same…
Accelerated K-Means and Mini-batch K-Means
Introduction Another important improvement to the K-Means algorithm was proposed in a 2003 paper by Charles Elkan. It considerably accelerates the algorithm by avoiding many unnecessary distance calculations: this is…
Implementation of K-Means Clustering in Machine Learning
Consider the unlabeled dataset represented in Figure below: you can clearly see 5 blobs of instances. The K-Means algorithm is a simple algorithm capable of clustering this kind of dataset…