Please enable JavaScript.

Coggle requires JavaScript to display documents.

AI (types (narrow AI (handles one task only), AGI artificial general…

- - - - deep learning
        
        mathematical, deep equations
        
        Several layers of simple processing units, connected in a network
        
        Inputs are passed through each one of the layers
      - Neurons
        
        Stand processors, waiting for signals
        
        activation function
        
        done after the liear regression calculation
        
        includes
        
        identity function
        
        = output of linear regression
        
        step function (ON/OFF)
        
        imitates real neurons
        
        sigmoid function
        
        numerical levels of activation
      - Dendrites/axons
        
        Connections/wires between neurons
      - Key features
        
        Neurons process vast amounts of information simultaneously (instead of CPU)
        
        Data storage (memory) and processing aren’t separated
    - - supervised learning
        
        binary classification problems
        
        Nearest neighbor
        
        based on a number of examples and its correlaction to the correct label
        
        Linear regression
        
        Applicable when result may be a number, rather than a class
        
        Components
        
        Inout
        
        Output
        
        Intercept
        
        Noise
        
        Coefficients/weights
        
        Logistic regression
        
        Used to turn linear regression outputs into predictions about labels
        
        The correct answers are available to train/compare
      - unsupervised learnings
        
        data visualizations
        
        grouping data in clusters
        
        Correct answers aren’t provided
        
        Example: models group data and users define labels (loyalty cards programs)
        
        Generative modeling
        
        Given some data, model can generate more of the same (people’s face from pictures, e.g.)
      - reinforcement learning
        
        based on feedback about the decisions taken
    - - Do not become too confident about the accuracy of predictions
      - Separate data
        
        Training data
        
        Test data
      - Dont’t make the rules fit the past data perfectly
      - Filter bubbles #
    - - Hardness of task
      - ML method
      - Amount of training data
      - Quality of data
- - - - X:Y = For each X occurrences, you will have Y opposite occurencies
      - X/Y = you will have X occurrences out of Y total occurrences (including X)
      - It’s easier to intuitively understand odds instead of percentages
- - - - foxes: many small ideas
        
        better at predictions
      - hedgehogs: one big idea
    - - superintelligence will not evolve from developing narrow AI methods to solve real world problems
      - singularity: exponential intelligence face growing problems that slows down its progress
      - real threat = Terminator headlines diverts the attention from the actual problems
  - - - caused by human bias in data
      - human discrimination
        
        online advertising
        
        social networks
      - AI and machine learning are less transparent than simple rules
      - European General Data Protection Regulation (GDPR)
        
        right of access
        
        right to be forgotten
        
        right to explanation