You are on page 1of 1

1.

Introduction to Machine Learning through comparison between Human and Computer


performance.
2. Importance of Data used for Training and Testing.
3. Introduction to Classification Problems.
4. One Model for All Classes (Human Brain) vs One Model for One Class (Statistical Laerning
Problem).
5. Introduction to characteristics, feature or attributes vectors.
6. Discriminative vs Non Discriminative solutions to problems.
7. Introduction to Neural Networks
8. Artificial Neural Network Layered Architecture.
a. Perceptron Algorithm
b. Convergence Algorithm
9. Supervised and Unsupervised Learning.
10. Epoch
11. Gradient Descent rule.
12. Back propagation algorithm with graph.
13. Learning weight adjustment.
14. Incremental Learning
a. Discriminative learning
b. N model for N classes
15. Introduction to speech recognition.
16. K-Nearest Neighbor algorithm
a. Distance Measurement
i. Euclidian Distance
ii. Mahalanobis Distance
iii. Cosine Similarity Distance.
b. KNN advantages and disadvantages.
17. Decision Tree Learning with example playing game Yes/No
a. Characteristics
b. Entropy
c. Information Gain
18. Normal / Gaussian distribution with graph.
19. Multivariant Normal Distribution.
20. Introduction to Baye’s Theorem.

You might also like