Scribd
Upload
11 views3 pages

REM

The document discusses an overview of machine learning topics that could be covered over 10 days. It includes introductions to supervised and unsupervised learning, preprocessing, optimization, classification algorithms like logistic regression and SVMs, regression, clustering, Bayesian methods, graphical models, neural networks and other miscellaneous topics.

Uploaded by

hassenhachicha1
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
11 views3 pages

REM

The document discusses an overview of machine learning topics that could be covered over 10 days. It includes introductions to supervised and unsupervised learning, preprocessing, optimization, classification algorithms like logistic regression and SVMs, regression, clustering, Bayesian methods, graphical models, neural networks and other miscellaneous topics.

Uploaded by

hassenhachicha1
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

What is CV ?

What would you do to satisfy your client ? roc curve

Non parametic models (DT) doesn’t require scaling / LR knn and svm we use scaling

correlation matrix for categorical variables and continous variable

https://vitalflux.com/interns-machine-learning-interview-questions-with-answers-set-1/

https://skillvalue.com/en/quiz/machine-learning/
Day 1:

• Basic terminology:
a. Most common settings: Supervised setting, Unsupervised
setting, Semi-supervised setting, Reinforcement learning.
b. Most common problems: Classification (binary & multiclass),
Regression, Clustering.
c. Preprocessing of data: Data normalization.
• Concepts of hypothesis sets, empirical error, true error, complexity of
hypotheses sets, regularization, bias-variance trade-off, loss
functions, cross-validation.
Day 2:

• Optimization basics:
a. Terminology & Basic concepts: Convex optimization,
Lagrangian, Primal-dual problems, Gradients &
subgradients, ℓ1ℓ1 and ℓ2ℓ2 regularized objective
functions.
b. Algorithms: Batch gradient descent & stochastic gradient
descent, Coordinate gradient descent.
c. Implementation: Write code for stochastic gradient descent
for a simple objective function, tune the step size, and get an
intuition of the algorithm.
Day 3:

• Classification:
a. Logistic Regression
b. Support vector machines: Geometric intuition, primal-dual
formulations, notion of support vectors, kernel trick,
understanding of hyperparameters, grid search.
c. Online tool for SVM: Play with this online SVM tool (scroll
down to “Graphic Interface”) to get some intuition of the
algorithm.
Day 4:

• Regression:
a. Ridge regression
• Clustering:
a. k-means & Expectation-Maximization algorithm.
b. Top-down and bottom-up hierarchical clustering.
Day 5:

• Bayesian methods:
a. Basic terminology: Priors, posteriors, likelihood, maximum
likelihood estimation and maximum-a-posteriori inference.
b. Gaussian Mixture Models
c. Latent Dirichlet Allocation: The generative model and basic
idea of parameter estimation.
Day 6:

• Graphical models:
a. Basic terminology: Bayesian networks, Markov networks /
Markov random fields.
b. Inference algorithms: Variable elimination, Belief
propagation.
c. Simple examples: Hidden Markov Models. Ising model.
Days 7–8:

• Neural Networks:
a. Basic terminology: Neuron, Activation function, Hidden layer.
b. Convolutional neural networks: Convolutional layer, pooling
layer, Backpropagation.
c. Memory-based neural networks: Recurrent Neural Networks,
Long-short term memory.
d. Tutorials: I’m familiar with this Torch tutorial (you’ll want to
look at 𝟷𝟷_𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜𝚜1_supervised directory). There
might be other tutorials in other deep learning frameworks.
Day 9:

• Miscellaneous topics:
a. Decision trees
b. Recommender systems
c. Markov decision processes
d. Multi-armed bandits
Day 10: (Budget day)

• You can use the last day to catch up on anything left from previous days,
or learn more about whatever topic you found most interesting / useful
for your future work.

You might also like