Please enable JavaScript.
Coggle requires JavaScript to display documents.
introduction - Coggle Diagram
introduction
ARTIFICIAL INTELLIGENCE
DEFINITION
EFFORT
AUTOMATE
INTELLECTUAL
TASKS
GENERAL FIELD
MACHINE LEARNING
DEEP LEARNING
SYMBOLIC AI
HANDWRITTEN
RULES
INSUFFICIENT
MORE COMPLEX
TASKS
FIUGRE OUT
EXPLICIT RULES
MACHINE LEARNING
TRAINED
EXAMPLES
TASK
FIND
STATISTICAL STRUCTURE
COME UP
RULES
AUTOMATE
TASK
NEEDED
EXAMPLES
EXPECTED
OUTPUT
WAY
MEASURE
ACCURACY
ALGORITHM
IMPUT DATA POINTS
INPUT DATA
GET
OUTPUT
GET
DESIRED
REPRESENTATION
CONVERT
TO
OUTPUT
FORMAT
INPUTS
POINTS
BLACK
WHITE
OBJECTIVE
FIND
WHETHER
POINTS
WHITE
BLACK
(FEEDBACK)
VERIFY
ACCURACY
POINTS
CORRECTLY
FOUND
DEEP LEARNING
LAYERS
NUMBER
DEFINED
DEPTH
LAYERED REPRESENTATION
NEURAL NETWORKS
MAPPING
INPUT
DEEP SEQUENCE (SIMPLE DATA TRANSFORMATIONS)
LEARNED
1 more item...
TARGET
REPRESENTATION
DATA
WEIGHT
STORE
LAYER
DOES TO
INPUT DATA
PARAMETRIZE
TRASNFORMATION
LAYERS
PROBLEM
BILLIONS OF PARAMETERS
INITIALLY
RANDOM VALUES
LEARNING
FIND
SET OF VALUES
LOSS FUNCTION
PREDICTION
NETWORK
COMPUTE
DIFFERENCE
TARGET
OPTIMIZER
ADJUST
WEIGHTS
REDUCE
ERROR
BACKPROPAGATION
ALGORITHM
MONITOR
NETWORK
PERFORMANCE
COVERS
DEFINITIONS
FUNDAMENTAL CONCEPTS
INTRODUCTION
CONTEXT
MACHINE LEARNING
DEEP LEARNING
ARTIFICIAL INTELLIGENCE
APPLICATION
SELF-DRIVING CARS
VIRTUAL ASSISTANTS
INTELLIGENT CHATBOT
QUESTIONS
CAN
COMPUTER
LEARN
ON ITS OWN
LOOKING
DATA
HOW
REPRESENTATIONS
DEEP LEARNING ALGORITHM
LOOK LIKE
MACHINE LEARNING
DEEP LEARNING
