Artificial Intelligence
Intelligent behavior in machines: reasoning, search, planning, language and perception.
What is Artificial Intelligence?
Start learning from zero.
Artificial intelligence (AI) is the field of building computer systems that perform tasks associated with human intelligence—such as understanding language, recognizing images, making predictions and planning actions. You do not need to know calculus or Python to understand the basic ideas.
Start with the concepts. Learn Python and data handling as you progress. Work through examples, not just definitions.
How does AI actually work?
Traditional programs follow instructions written explicitly by a programmer. Many modern AI systems, especially machine-learning systems, learn patterns from examples. A trained model uses those patterns to produce an output for new input.
1. Collect data→2. Train a model→3. Evaluate it→4. Predict on new data→5. Monitor results
A simple example: filtering spam
Show a model emails labelled “spam” or “not spam”. It learns clues in words and messages. When a new email arrives, it predicts a label. Check predictions using unseen test emails: a model can make mistakes, and its performance may change over time.
Important: Not all AI uses machine learning, and generative AI can produce inaccurate or invented information.
AI, ML, deep learning and generative AI
Machine Learning
Algorithms learn patterns from data instead of relying only on hard-coded rules.
Deep Learning
Multi-layer neural networks learn useful representations from examples.
Generative AI
Models produce text, images, audio or other content; many use deep learning.
Where do we use AI?
🏫 Education
Personalized practice, translation and feedback, with teacher oversight.
🏥 Healthcare
Helping analyze scans and records; expert review remains essential.
đźšś Agriculture
Crop-image analysis, irrigation planning and weather-based decision support.
đź’¬ Language
Search, translation, summarization and speech recognition.
Interactive programming lab
🤖 Learn robotics by coding — RoboLab
Start with six beginner robot missions, then learn wheel motor control, distance sensing, obstacle avoidance and line tracking in six Level 2 challenges. All 12 missions run in your browser without robot hardware.
A practical roadmap for beginners
Follow these topics in order. The learning time varies; understand each stage before moving on.
Understand AI
Models, data, training, prediction, bias and responsible use.
Learn the foundations →Python and data
Variables, lists, NumPy, Pandas, basic charts and clean datasets.
Explore CSV with Pandas →Statistics and ML
Mean, variation, regression, classification and evaluating predictions.
Statistics lessons →Build useful projects
Try real data, compare results, document limits, repeat.
Practice projects →Try a prediction yourself
Imagine a plant grows about 2 cm per week. Estimate its height gained over a number of weeks. This simple rule-based illustration introduces prediction; it is not a trained AI model.
Predicted growth: 8 cm
A real machine-learning system learns a relationship from observations and should be tested on data it has not seen.
What should I know before starting?
Do I need to code?
No, not to begin. Python becomes helpful when you start building models.
Do I need advanced maths?
Start with averages, percentages and graphs; add algebra, statistics and linear algebra gradually.
How can AI go wrong?
Biased data, leakage, poor evaluation, privacy issues and hallucinations can cause unreliable outputs.