Novus Hi-Tech Interview Questions and Answers

I am passionate about applying my engineering skills to solve real-world problems and contribute to innovative projects.

• Passionate about engineering and problem-solving

• Excited about contributing to innovative projects

• Seeking opportunities for professional growth and development

My future plans include gaining experience in the engineering field, pursuing further education, and eventually taking on leadership roles.

• Gain experience in the engineering field through internships and entry-level positions

• Pursue further education such as a master's degree or specialized certifications

• Work towards taking on leadership roles within a company or starting my own engineering firm

Bias is error due to overly simplistic assumptions in the learning algorithm, while variance is error due to too much complexity.

• Bias is error from erroneous assumptions in the learning algorithm, leading to underfitting.

• Variance is error from too much complexity in the learning algorithm, leading to overfitting.

• Bias and variance are inversely related - increasing one decreases the other.

• Balancing bias and variance is ...read more

Yes, I have trained a convolutional neural network from scratch to classify images of different dog breeds.

• Researched and collected a dataset of images of various dog breeds

• Preprocessed the images by resizing and normalizing them

• Designed a convolutional neural network architecture using TensorFlow

• Trained the model using the dataset and adjusted hyperparameters for better performance

• Evaluated the model's performance usi...read more

Loss functions are used in machine learning to measure the inconsistency between predicted and actual values.

• Mean Squared Error (MSE) - measures the average squared difference between predicted and actual values

• Mean Absolute Error (MAE) - measures the average absolute difference between predicted and actual values

• Binary Cross Entropy - used for binary classification tasks

• Categorical Cross Entropy - used for multi-class...read more