CS代考程序代写 AI LECTURE 2 TERM 2:

LECTURE 2 TERM 2:
MSIN0097
Predictive Analytics Video 4: Optimisation
A P MOORE

MACHINE LEARNING
Data + modelàprediction

MACHINE LEARNING DATA DRIVEN AI
Assume there is enough data to find statistical associations to solve specific tasks
Data + modelàprediction Define how
to maximize performance
adapt the parameters
well the model solves the task and

A – B – C- D
A TAXONOMY OF PROBLEMS
A. ClAssification B. Regression Week 2 – Classification and Regression
Week 3 – Trees and Ensembles
C. Clustering D. Decomposition
Week 5 – Clustering
Week 4 – Kernel spaces and Decomposition

END- TO-END
— Discover — Explore — Visualize
— Clean
— Sample — Impute — Encode — Transform
– Scale — Features — Pipelines
— Documentation — Presentation
— Launch — Monitor — Maintain
— Training/Validation splits — Modeling
— Tuning
— Error Analysis

END- TO-END
— Discover — Explore — Visualize
— Clean
— Sample — Impute — Encode — Transform
– Scale
— Modeling
– Overfitting
– Optimization
– ModelSelection – Regularization
– Generalization
— Documentation — Presentation
— Launch — Monitor — Maintain

LEARNING A FUNCTION
𝑥→𝑦
𝑥 →𝑓(𝑥)→𝑦

LEARNING A FUNCTION
𝑥→𝑦
𝑥 →𝑓(𝑥)→𝑦
Measured data
Features Inferred/Predicted/Estimated value
Trueinitialvalue𝑥 →𝑥’→𝑓 𝑥 =𝑦’ →𝑦
(world state) True target value
Learned/Fitted function (world state) From n observations

COMPONENTS OF A
MACHINE LEARNING SOLUTION

B. REGRESSION REAL VALUED VARIABLE

array([[4.21509616], [2.77011339]])

MAKING PREDICTIONS

ERROR SURFACE

GRADIENT DESCENT

LEARNING RATE TOO SMALL

LEARNING RATE TOO LARGE

MINIMA AND PLATEAUS

ERROR SURFACES

(NON) CONVEX

PARTIAL DERIVATIVES IN PARAMETER SPACE

FEATURE SCALING

LEARNING RATES

STOCHASTIC GRADIENT DECENT

PATHS IN THE SEARCH SPACE

LEARNING SCHEDULE

OP TIMIZERS

OPTIMIZERS A2GR ADEXP

OP TIMIZERS ADABELIEF

HYPER-PARAMETERS

FINE- TUNING

GRID SEARCH

RANDOM SEARCH

TRAINING EPOCHS

ERROR SURFACES

EARLY STOPPING

PROGRAM SPACE
Source: https://medium.com/@karpathy/software-2-0-a64152b37c35

CRISP CYCLE
DATA DEVELOPMENT LIFECYCLES

LECTURE 1 TERM 2:
MSIN0097
Predictive Analytics
A P MOORE

Leave a Reply

Your email address will not be published. Required fields are marked *