Artificial Intelligence Flashcards
What is AI?
AI (Artificial Intelligence) refers to the simulation of specific human cognitive capabilities in machines that are programmed and managed by humans to perform complex tasks.
Machine learning
Characteristics
machines learn from data and improve over time without being explicitly programmed to perform a specific function.
Helps in pattern recognition.
Deep learning
Deep Learning is a type of machine learning that uses neural networks to mimic the way our brains work.
DL powers voice assistants.
NLP
Natural Language Processing or NLP helps machines understand and interact with human language.
Translate languages understand texts and much more
AI Evolution
All evolved advancements were made possible by the exponential growth of computing power and data availability.
Narrow AI
Also known as weak AI, is designed to perform a specific task or set of tasks with a high level of proficiency, such as facial recognition or language translation. It is considered “narrow” because it lacks the ability to understand, learn, and apply knowledge beyond its programmed domain.
Example of Narrow
Siri and Alexa, chatbots found in apps and on websites, and recommendation algorithms used by Netflix, Amazon, and Spotify.
General AI
General AI
(Strong AI)
, is a theoretical form of AI that possesses the ability to understand, learn, and apply knowledge across a wide range of tasks at the level of human intelligence. There are currently no examples of general AI systems, as the technology does not yet exist.
Types of AI
1.Narrow AI
2.General AI
The Role of Data in AI
The Role of Data in AI
Data serves as the foundation of AI providing the raw material from which models learn, make predictions, and generate insights.
well-prepared data leads to more accurate and reliable outcomes, while poor-quality data can result in biased or flawed models.
Importance of big data in AI
Importance of data in AI
Big data plays a significant role in training sophisticated AI systems, large and diverse datasets enhance the models’ ability to handle complex tasks, as seen in applications such as language translation and autonomous vehicles.
Data Preprocessing and techniques
Data Preprocessing
Ensures that the data used in an AI model is clean, consistent, and ready for analysis, thereby improving model accuracy and performance.
Preprocessing techniques include: Handling missing & incomplete data, normalization, scaling, and data transformation.
Data Cleaning
Involves identifying and correcting errors within datasets, including outliers and data “noise” to maintain the model’s integrity.
Data Outliers
Outliers are data points that differ significantly from other observations.
They can skew results and need to be addressed, either by removing them or using techniques to reduce their impact.
Data Noise
Data Noise refers to irrelevant or meaningless data
that can interfere with the analysis. This can be anything from random errors to irrelevant information.
