Steps to become a Machine Learning Engineer :-

Steps 1:-Introduction to ML : –

Overview of Topics :- Machine learning problems, parameter vs. hyperparameter, overfitting, training, validation, testing, cross-validation, regularization

Step2:- Classifications Algorithms :-

Overview of Topics :- Definition of a decision tree, metrics of impurity, greedy algorithm to split a node, tree depth and pruning, ensemble of trees (random forest)

Step 3 :- Bayesian Decision Theory :-

Overview of Topics :- Bayes rule: Prior, likelihood, posterior, evidence, Gaussian density, sufficient statistics, maximum likelihood derivation for mean and covariance

Step 4 :- Linear models :-

Overview of the Resources :-

linear regression and its analytical solution, loss function, gradient descent and learning rate, logistic regression and its cost, SVM: hinge loss with L2 penalty.

Step 5 :- Kernelization :-

Overview of the Resources :-

Dual form of an SVM, kernels for a dual form, examples of kernels and their typical uses, SVR in primal form, SVR in dual form.

Step 6 :- Feature Selection and Engineering :-

Overview of the Resources :-

T-test, forward selection, features for images, features for audio, features for images, features for NLP, PCA, ZCA, K-PCA.

a) Supervised Features selections :

b) 10 Effective Techniques on Feature Selections :-

c) Image Fundamentals :-

d) Audio Fundamental :-

e) Music Features Extractions in Python :

Step 7 :- Dense and shallow neural networks :-

Overview of Topics : –

Logistic regression as a sigmoid, single hidden layer using sigmoid and ReLU, approximation of any function using a single hidden layer, overfitting, advantage of multiple hidden layers, neural networks for regression, multi-regression, multi-classification using softmax, back propagation.

a) Multilayer perceptron :-

b) Visual proof for NN computing :-

d) Forward propagations, Backward propagations and Computational Graphs :-

Steps 8: Advanced topics in neural networks :-

Overview of the Resources :-

Weight initialization, momentum, weight decay, early stopping, batch SGD, advanced optimizers such as RMSprop and ADAM.

Training Neural Network 1
Training Neural Network

Step 9:- Clustering

 Overview of the Resources :- K-means, DB-SCAN, agglomerative clustering, scaling of dimensions, goodness of clustering.

Clustering Stanford Andrew NG
Prof Sudeshna IITKgp

HURRAH!!!!! You are Eligible for Machine Learning Engineer.

Share This Post
Have your say!
Skip to toolbar