Picking between GOFAI, ML, and Deep Learning (Summary)

Answering the million-dollar question

4 min readJan 24, 2024

Picking between Deep Learning, Traditional Machine Learning, or GOFAI is a multi-million-dollar question on everyone’s mind.

Here is how I see it- GOFAI and Pure Deep Learning exist on opposite ends of the spectrum for many key factors (amount of domain knowledge needed, data requirements, costs, transparency, etc) with ML splitting the difference.

Based on all these factors, I conclude the following-

Traditional AI- The most secure, understandable, and performant. However, Good implementations of traditional AI require that we define the rules behind the system, which makes it unfeasible for many of the use cases that the other 2 techniques thrive on. Contrary to popular belief, well-designed GOFAI agents can actually beat Deep Learning/Machine Learning agents, as was seen in the following research- “The margin of victory was significant, with the top symbolic agent beating the top neural agent by a factor of almost 3 in the median score. This was, in fact, increased when looking at the very best agents from each team, where frequently we might see almost an order of magnitude improvement in the median score between the best symbolic and neural agents…While our best symbolic teams had moderate-to-expert NetHack domain understanding, we were surprised to find they often had extensive ML experience as well. In fact, both winning symbolic teams said they had intended to enter the neural track, but found their symbolic methods scaled much better…” The challenge with these is actually building performant systems, which requires a lot of domain understanding and expertise. Don’t overlook GOFAI when you can clearly define the rules of engagement.
Supervised Machine Learning- Middle of the road b/w AI and Deep Learning. Good when we have some insight into the workings of the system, but are unable to create concrete, well-defined rules for it. Machine Learning models + Feature Engineering can bring some serious heat in performance

In this paper, we compare the performance of four different PLMs on three public domain-free datasets and a real-world dataset containing domain-specific words, against a simple SVM linear classifier with TFIDF vectorized text. The experimental results on the four datasets show that using PLMs, even fine-tuned, do not provide significant gain over the linear SVM classifier. Hence, we recommend that for text classification tasks, traditional SVM along with careful feature engineering can pro-vide a cheaper and superior performance than PLMs.
-Source. Just the addition of a few well selected features can add soo much to your performance.

Deep Learning- Opaque and costly, far too many teams rush to use Deep Learning when other solutions would suffice. However, with very unstructured data, where identifying rules and relationships is very difficult (even impossible), Deep Learning can be the only way forward.

To read about the conclusions in greater depth, read the my article, “How to Pick between Traditional AI, Supervised Machine Learning, and Deep Learning” below

How to Pick between Traditional AI, Supervised Machine Learning, and Deep Learning [Thoughts]

The framework I use to determine what tool to use for your problems

artificialintelligencemadesimple.substack.com

If you liked this article and wish to share it, please refer to the following guidelines.

If you find my writing useful and would like to support my writing- please consider becoming a premium member of my cult by subscribing below. Subscribing gives you access to a lot more content and enables me to continue writing. This will cost you 400 INR (5 USD) monthly or 4000 INR (50 USD) per year and comes with a 60-day, complete refund policy. Understand the newest developments and develop your understanding of the most important ideas, all for the price of a cup of coffee.

Support AI Made Simple