Deep Learning

All Blogs

Attention Mechanisms on EEG Data: What Actually Works

Part one answered "what is attention - How they let a model focus on what matters in a sequence rather than treating everything equally. This post answers a harder question: Does it actually work? I pulled attention mechanisms out of their comfort zone (text, language models, translation tasks) and dropped them into something messier: raw brain signals. The question was simple. Do these techniques actually hold up when the data isn't words in a sentence — but electrical acti

ravula greeshma

Jun 65 min read

Attention Mechanisms: What They Are, How They Work, and Why They Matter

Here's what actually sparked my interest in Attention Mechanisms Back in 2021, I was working on a research study - "EEG Emotion recognition using DEAP dataset" EEG (Electroencephalogram) - if you haven't heard of it, is basically a way to record electrical activity in your brain ,you wear a headset with electrodes, and it captures your brainwaves in real time. The DEAP dataset is a collection of EEG recordings from 32 participants who watched music videos, with their emotio

ravula greeshma

Jun 55 min read

Without k-Anonymity, a unique individual may stand out within a dataset, increasing the risk of re-identification. After applying k-Anonymity, records become part of a larger group, making it more difficult to distinguish any single individual.

The Basics of k-Anonymity: Making Individuals Harder to Identify

k-Anonymity is a privacy-preserving technique designed to reduce the risk of identifying individuals in a dataset. The central idea is simple: each record should be indistinguishable from at least k − 1 other records based on a selected set of attributes.

Swetha Srihari

Jun 56 min read

Figure 1. Data collected from everyday online activities can be used to personalize services and advertisements, highlighting the growing importance of protecting individual privacy in machine learning systems.

The Privacy Challenge in Machine Learning

I had always believed that we can maintain privacy by not revealing too much information about ourselves in online forums and social media. But my perspective changed whenI took a course during my graduate studies called “Privacy Aware Computing”. I attended the first lecture without even enrolling in the course because I wanted to know if it was something that would interest me. I was not expecting much. But I was so drawn by the subject. That single lecture was enough to c

Swetha Srihari

Jun 47 min read