The most certain way to succeed is always to try just one more time.
—Thomas Edison
How it all started
Back in 2022, I was browsing through a tech community group on WhatsApp that I had just joined, when I saw someone drop a link to apply for the Kaggle Mentorship Programme for the 2022 cohort. At the time, I was just starting to learn about data science, but I thought, "This programme is organised by Kaggle—they surely have plenty of resources to mentor me into becoming a data scientist. So, yes, let me apply."
You can probably guess what happened. Well, I wasn’t selected.
Fast forward to 2023, I had started taking some data science courses and building projects. The opportunity to apply for the Kaggle mentorship came up again, and once more, I applied. But again, I wasn’t selected.
My thought at that point was, maybe I need to upskill more to have the right skill set to be mentored.
This was me encouraging a fellow candidate who wasn’t selected in 2023.
"You miss 100% of the shots you don’t take." This famous quote by Wayne Gretzky, a hockey player, is often a reminder for me to take action to achieve my goals.
The opportunity came up again this year, 2024. I gave it another shot, and I finally got accepted! It’s a win for me, and the first thing I did was announce my success on Twitter.
What is the Kaggle X fellowship programme all about?
At this point, you might be wondering what the program is all about and why I am so excited about being accepted into it and completing it.
The KaggleX Fellowship Program is designed to enhance representation and create career opportunities for Black, Indigenous, and People of Color (BIPOC) in the data science industry, the program pairs early to mid-career practitioners with experienced mentors.
Participants gain hands-on experience by working on impactful data science projects for their portfolios, while benefiting from a supportive, community-driven environment that encourages personal and professional growth.
So, you can see why I was persistent in getting into the program. I am aware of the lack of opportunities available to me, so I wanted to participate and learn from mentors and industry practitioners.
Highlights of My Journey in the Program
This year's cohort focused on working with LLMs. Specifically, every participant had to fine-tune the Google Gemma model for a question-and-answer task in different domain use cases.
Therefore, a participant interested in healthcare, for instance, can fine-tune the Google Gemma model to answer questions related to cancer.
My Project
I am interested in the application of AI/ML to solve problems in cybersecurity, and I thought of a good use case that would be applicable. I fine-tuned Gemma to act as a cybersecurity help desk chatbot.
This AI-driven help desk is designed to answer cybersecurity-related questions for employees, ensuring efficient support and enhancing organizational security protocols. It provides employees with 24/7 access to cybersecurity guidance.
The chatbot could answer questions such as:
- What should I do if I suspect a phishing attempt?
- How do I know if my computer is infected with malware?
- What should I do if I think my computer has been hacked?
- How can I securely back up my data?
- How do I know if an email attachment is safe to open?
Final Outcome
The program lasted for 15 weeks. During that time, in addition to building a chatbot, I achieved a lot that would ordinarily have taken me much longer. Below are the accomplishments I achieved throughout the program.
Built a Chatbot
The main focus of the program was to build a portfolio, and I participated in and completed the development of a cybersecurity help desk chatbot. Through building the chatbot, I learned about LoRA fine-tuning of LLMs, and how to generate synthetic data to fine-tune LLMs, and I also wrote a blog about it.
One-on-One Mentoring
I was assigned a one-on-one advisor Samuel Waweru, and I gained a lot from his guidance. Through our weekly one-on-one calls, I was able to build and complete the chatbot. He often shared opportunities for me to apply for internships.
Networked with Industry Experts
Apart from mentoring, I also had the opportunity to meet with other advisors from various industries, many of whom are experts in AI/ML from top organizations.
Published the First Variant of the Cybersecurity Chatbot Gemma Model on Kaggle
Kaggle allows users to publish pre-trained models to the Kaggle Model Hub. Previously, there was no variant of the Gemma model fine-tuned for cybersecurity use cases. I was able to publish the first one.
Conclusion
Rejections are not failures; they are opportunities to refine your approach and grow. By embracing persistence and following your curiosity, you open doors to possibilities that were once out of reach.
My journey into the KaggleX Fellowship Program is a testament to the power of staying committed to your goals and continuously improving yourself, even in the face of rejection. Each attempt, whether successful or not, was a stepping stone towards gaining valuable skills.
Following my curiosity led me to explore the intersection of AI and cybersecurity, an area I am deeply passionate about. This led me to create something impactful—a fine-tuned chatbot that addresses real-world challenges.
Project outcome
Here is how the Gemma model responds to cybersecurity queries before fine-tuning. Initially, it had limited knowledge in the security domain.
After fine-tuning, however, the Gemma model gained expertise in this domain and now functions effectively as a cybersecurity help desk.
Top comments (0)