Machine Learning (CY-701) - Important Questions

Explain the major limitations of machine learning.

Explain the role and importance of data preprocessing in machine learning and why it is needed.

Discuss in detail the types of data visualization in ML.

What is the need for data augmentation? Discuss about data augmentation.

Explain the machine learning concept by taking an example. Describe the perspective and issues in machine learning.

Define machine learning. Discuss regression analysis in detail.

Explain the role of backpropagation in training a multilayer network and how weights are adjusted through successive layers.

What is the ReLU activation function? Compute its output for given inputs.

Explain the working of batch normalization. Write its benefits and usage areas.

What is an activation function? Discuss its types with suitable formulas.

Explain the difference between linearity vs. non-linearity model.

What is the gradient descent algorithm in ML? Explain.

What is the purpose of the sigmoid activation function in Machine Learning?

Explain the Inception network architecture and how Inception modules use multiple kernel sizes simultaneously to improve efficiency.

Explain the implementation of Convolutional Neural Network (CNN) in TensorFlow.

Explain the concept of padding in CNNs, including types such as valid and same padding and their influence on preservation of spatial features.

Explain how max pooling reduces dimensionality. Given a $4\times4$ feature map. $$\begin{bmatrix} 1 & 2 & 3 & 0 \\ 4 & 5 & 6 & 1 \\ 7 & 8 & 9 & 2 \\ 0 & 1 & 2 & 3 \end{bmatrix}$$ Apply $2\times2$ max pooling with stride 2 and show the resulting matrix.

What is the purpose of using a $1\times 1$ convolution in CNNs, and how does it contribute to feature reduction and model efficiency?

What is sub sampling and how does it contribute to feature extraction?

Discuss the concept of Dimensionality Reduction.

Explain the concept of Recurrent Neural Network (RNN).

Explain the difference between the SARSA and Q-learning algorithms in terms of updating Q-values.

Explain the role of beam width in beam search and how it affects performance.

Explain Q-learning and compare Q-learning vs SARSA.

How does reinforcement learning differ from supervised and unsupervised learning?

Discuss in detail about Actor-critic model.

Differentiate between Value Iteration and Policy Iteration.

Give an overview of / explain Q-learning.

Explain the applications of machine learning in speech recognition, synthesis and speech processing.

Explain what a Support Vector Machine is and how it finds the optimal maximum-margin hyperplane for classification with a linear SVM.

Discuss in detail about Bayesian learning.

Write short notes on :

List and explain application of machine learning in computer vision.

Write short notes on any two of the following

Explain any two of the following :