Hello everyone! How are you? Today, I will talk about a topic that is both very cool and transforming our lives: Artificial Intelligence! You know, like in movies where robots take over the world… Of course, it’s not so exaggerated, but it has really seeped into every aspect of our lives. I thought I’d glance over its main branches for those just starting on this path, as if we’re sitting side by side and chatting.
Now, when we hear Artificial Intelligence, we immediately think of those super intelligent robots, right? But actually, what we call AI is a vast field built around making machines think, learn, and solve problems like humans. Of course, explaining this under a single umbrella is challenging. So it’s divided into many subfields. The most popular ones are Machine Learning, Natural Language Processing (NLP), and Computer Vision. Let’s get to know these a bit more closely.
First, let’s start with Machine Learning. This is perhaps the most familiar part of AI. Think of teaching a child something new. You show them lots of examples, right? Machine learning works exactly like that. We give computers a vast amount of data, and they learn the patterns and rules from these data on their own. For example, the recommendations for movies on your Netflix or filtering spam emails are tasks of machine learning. My own programming class failed 🙂
Meanwhile, machine learning contains many different approaches. Supervised learning, unsupervised learning, reinforcement learning… But for now, there’s no need to delve deeply into these. What’s important is the logic: Provide data to the computer, let it learn. Isn’t that wonderful?
Next is Natural Language Processing, or NLP. This is a particularly enjoyable area for me. Imagine that computers understand our language, even converse with us… That’s what NLP is all about. Virtual assistants on our phones, translation programs, text analysis systems, all work thanks to NLP. You know sometimes when you type something into Google Translate and the output doesn’t make much sense, right? That’s when you realize how challenging NLP is. But the truth is, significant advancements have been made. Recent large language models (LLMs) are the biggest proof of this.
For example, I recently asked a friend, “Can we have AI write poetry?” They immediately showed me some links. I looked, and honestly, the poems weren’t bad. Of course, they’re not Shakespeare, but I think it’s worth a try. If you’re curious, you can search here.
Finally, we arrive at Computer Vision. This enables machines to “see” the world. It means analyzing a photo or video and recognizing objects, faces, scenes. Self-driving cars, facial recognition systems, software detecting anomalies in medical images—all are possible thanks to computer vision. Remember when your phone first used face recognition to unlock? It felt quite strange, huh?
In the meantime, these three subfields are deeply interconnected. Without machine learning, NLP and Computer Vision wouldn’t develop much. Analyzing data, recognizing patterns—is all machine learning’s job. They are part of a whole, really.
Now you might ask, “How do we get involved in these?” or “What should I do?” The simplest thing is to start by reading and researching a lot. The internet is an incredible resource. For example, there are many educational videos on YouTube. You can check here, I’m sure you’ll find something interesting.
Should we jump into coding? Of course! Python is one of the most used languages in AI projects. With machine learning libraries (like Scikit-learn, TensorFlow, PyTorch), you can do amazing things. For instance, using your data, you can perform simple classification. Suppose you have data on house sizes and prices, and you want to predict the price of a new house.
Let’s first try a very simple approach, like taking the average:
# WRONG APPROACH: Simple Average for Prediction houses = [ {"size": 100, "price": 200000}, {"size": 150, "price": 300000}, {"size": 200, "price": 400000} ]new_house_size = 120 total_price = sum(house["price"] for house in houses) total_size = sum(house["size"] for house in houses) avg_price_per_sq_m = total_price / total_size
estimated_price = avg_price_per_sq_m * new_house_size print(f"Estimated Price (Incorrect): {estimated_price} TL")
This is, of course, very basic and doesn’t give accurate results. Since prices depend on many other factors besides size. Here, machine learning steps in. With algorithms like linear regression, we can make much more accurate predictions. By the way, to use these algorithms, you need to install the relevant libraries, like pip install scikit-learn.
Now, let’s do the same with a more correct approach:
# CORRECT APPROACH: Linear Regression for Prediction from sklearn.linear_model import LinearRegression import numpy as np
houses = [ {"size": 100, "price": 200000}, {"size": 150, "price": 300000}, {"size": 200, "price": 400000} ]
# Convert data into numpy arrays X = np.array([house["size"] for house in houses]).reshape(-1, 1) # Sizes (independent variable) y = np.array([house["price"] for house in houses]) # Prices (dependent variable)
# Create and train model model = LinearRegression() model.fit(X, y)
# Predict the price of a new house new_house_size = np.array([[120]]) # Size of new house estimated_price = model.predict(new_house_size)[0]
print(f"Estimated Price (Correct): {estimated_price:.2f} TL")
As you can see, machine learning allows us to obtain much more reasonable and accurate results. This is just the tip of the iceberg. Artificial intelligence is an enormous field with new developments every day.
It's also very popular—it's everywhere. For example, Trendyol offers personalized product recommendations with AI. Or Hepsiburada has customer service bots. All of these are products emerging from the integration of these subfields.
In conclusion, AI is now part of our lives and will become even more important in the future. If you're interested in this field, take the first step without fear. Read a lot, explore, learn. Remember, every big journey begins with a small step. :) Maybe you will become one of the future's AI engineers, who knows?
That's all I have to share for now. I hope you didn't get bored and found it somewhat useful. If you have questions, don't hesitate to ask.
By the way, recently, my family and I went camping near Bursa. Sitting around the fire at night, watching the stars, I wondered how AI technologies might influence future camping experiences. Maybe a system that more accurately predicts the weather, or navigation that prevents us from getting lost in the camping area... Who knows, maybe someday we'll have AI companions while camping. But I think the best part for me will always be spending time with my wife and child in nature.