Machine learning
Machine learning is the approach to artificial intelligence Artificial intelligence is a computer system’s ability to perform tasks we associate with human intelligence, such as understanding language, recognizing images or making decisions. More in the glossary → in which a system learns from examples instead of someone writing each rule by hand. It is shown lots of data —images, text, numbers— and the model adjusts its parameters until it detects patterns it can then apply to new cases. For instance, after seeing thousands of emails marked as spam Spam is unwanted bulk messages, usually by email — often advertising, but sometimes a carrier for phishing or malware. More in the glossary → , it learns to recognize one it had never seen before. There is supervised learning (with labeled examples), unsupervised (it finds structure on its own) and reinforcement learning (it learns by trial and reward). Almost all modern AI, including large language models An LLM is an AI model trained on huge amounts of text to understand and generate language. It is the engine behind assistants like ChatGPT. More in the glossary → , is built on this principle. Its quality depends directly on the amount and quality of the training data Training data is the set of examples an AI model learns from. Its amount and quality determine how good —and how biased— the model will be. More in the glossary → .
Articles that cover it
- Antivirus EDR vs. antivirus: what is the difference? EDR records and investigates endpoint activity for security teams; antivirus prevents malware automatically. Which layer you need, explained clearly. Read article
- Antivirus How does antivirus software detect malware? Antivirus software detects malware with signatures, heuristics, behavior analysis and cloud ML. Here is how each layer works and why all are needed. Read article