In the realm of ever-evolving technology, the launch of chatGPT in late 2022 piqued my curiosity and ushered me into the magnificent world of machine learning. Despite my non-technical background, I was keen on unlocking the secrets that machine learning holds. My quest for knowledge led me to Coursera, where the highly acclaimed “Machine Learning Specialization” and “Deep Learning Specialization” by Stanford and Deeplearning.AI awaited. Recommended by many in my network and even by chatGPT itself, I embarked on a learning expedition with Andrew Ng at the helm.
Breaking Into AI with Machine Learning Specialization
The Machine Learning Specialization was my first foray into the domain. Created by Stanford Online and DeepLearning.AI, this beginner-friendly program promised a comprehensive introduction to machine learning fundamentals, from building ML models with NumPy & scikit-learn to applying unsupervised learning techniques.
Who’s at the Helm?
Leading the course is none other than AI visionary, Andrew Ng, whose groundbreaking work at Stanford University, Google Brain, and Baidu has significantly advanced the AI field, offering a rich blend of theoretical knowledge and practical application.
What I Learned
The program provided me with a solid foundation, teaching me how to build machine learning models using Python, NumPy, and scikit-learn. I learned to construct and train supervised models for prediction and binary classification tasks.
Overcoming Challenges
The initial challenge was grappling with Python and the command line interface, but with chatGPT by my side, I found the courage to ask questions, no matter how simplistic, and slowly but surely, I started making headway. The journey of overcoming the fear of asking questions, paired with the insightful explanations received, significantly eased my learning curve.
Advancing My Skills with Deep Learning Specialization
Next on my learning agenda was the Deep Learning Specialization. This program, also instructed by Andrew Ng, dives deeper into the intricacies of machine learning, focusing on neural network architectures and cutting-edge techniques.
The Learning Curve
Transitioning from the basics to more advanced concepts was a steep learning curve. However, the well-structured curriculum and hands-on projects eased the transition, making the complex world of deep learning more approachable. There is a bit of overlap between this course and the course above. However, since it is online learning, you can fast forward or skip the content that you have learned before.
Gaining Practical Expertise
The real-world projects were the highlights, providing a platform to apply the theoretical concepts in practical scenarios. These projects weren’t just exercises but a bridge to real-world applications, demonstrating the transformative power of deep learning in addressing modern-day challenges.
Building Systems with ChatGPT API
Lastly, the course on Building Systems with the ChatGPT API opened up a new avenue for me to explore the integration of large language models into practical applications. Based on what I have learned from the previous two courses, I managed to:
- Export data from my website, which is built on WordPress
- Clean and prepare the data. You can check out some sample code here. Of course, the code needs to be revised further based on the project /API specification.
- Use embedding API to build a better search function using LLM.
The Intersection of Language and Code
This course taught how to automate complex workflows using chain calls to a large language model, enhancing my efficiency and development capabilities.
In Retrospect
Looking back, the journey was arduous yet enriching. With each course, not only did my understanding of machine learning deepen, but the horizon of what I could achieve with this knowledge expanded.
And guess what? I succeeded in building my chatbot using OpenAI API, embedding technology, etc… You can check out the lessons learned and the chatbot here.