Please enable JavaScript.
Coggle requires JavaScript to display documents.
AI (Machine Learning (Categorization (Text categorization, i.e. spam…
AI
Machine Learning
-
Types
Supervised learning
We already know the outcome B. So, give A we expect B.Input A -> Output B
eg.
- input email -> output spam (spam filtering)
- input audio -> text transcript (speech recognition)
-
-
-
Definition
"Field of study that gives computers the ability to learn without being explicitly programmed." Arthur Samuel (1959)
Running AI system, it serves users and learns from them
eg. website, mobile app
Algorithms Groups
Classification: A set of data is given, and your answer is one of the pieces of data.
-
Anomaly detection: Analyzes patterns, i.e. credit card fraud detection.
-
-
-
Categorization
Text categorization, i.e. spam filtering
Fraud detection, i.e. credit card fraud
Machine vision, i.e. image processing/face detection
Natural language processing, i.e. spoken language understanding
Market segmentation, i.e. predict if customer will respond to a promotion
Bioinformatics, i.e. pharmacy trying to understand if an antibiotic will treat a cold
Data
dataset - structured data
image, audio, text - unstructured data
-
Mis-use
It's not good just collecting data to use it later. Start using it early to train your AI, then you can say if data is good or not.
Huge of data, but bad data is not valuable
-
Types
ANI - Artificial Narrow Intelligence
Focus on to solve one problem.
eg. Self-driving cars, translation, diagnostics, speech recognition...
-
Data Science
Definition
"science of extracting knowledge and insights from data"
Dataset analyzed to get insights into the business, for example, or to make decisions
Projects
Key Steps of a Project
-
Suggest hypotheses/actions
- Deploy changes
- Re-analyze new date periodically
-
-
Tools
ML Frameworks
- TensorFlow
- PyTorch
- Keras
- MXnet
- CNTK
- Caffe
- PaddlePaddle
- Scikit-learn
- R
- Weka