Ar Ramaswamy Estates Interview Questions and Answers

Supervised ML uses labeled data to train models, while Unsupervised ML finds patterns in unlabeled data.

• Supervised ML requires labeled data for training

• Unsupervised ML finds patterns in unlabeled data

• Supervised ML includes tasks like classification and regression

• Unsupervised ML includes tasks like clustering and dimensionality reduction

• Example of Supervised ML: predicting house prices based on features like location and size

• Example of Unsupervised ML: grouping customers based...read more

RAG (RAGS) stands for Read, Attend, Generate. The flow of data in RAG involves reading input, attending to relevant information, and generating output.

• Data is first read as input

• The model attends to relevant parts of the input

• Finally, the model generates an output based on the attended information

Artificial Intelligence is the simulation of human intelligence processes by machines, especially computer systems.

• AI involves machines performing tasks that typically require human intelligence, such as visual perception, speech recognition, decision-making, and language translation.

• Examples of AI include virtual assistants like Siri and Alexa, self-driving cars, recommendation systems like Netflix's algorithm, and facial recognition technology.

• AI can be categorized into nar...read more

Machine learning is a branch of artificial intelligence that enables systems to learn and improve from experience without being explicitly programmed.

• Machine learning is a subset of artificial intelligence that focuses on developing algorithms and models that allow computers to learn from and make predictions or decisions based on data.

• It involves training a model on a dataset to recognize patterns and make predictions or decisions without being explicitly programmed.

• Examples...read more

Deep learning is a subset of machine learning that uses neural networks to model and solve complex problems.

• Deep learning involves training neural networks with multiple layers to learn representations of data.

• It is used in various applications such as image and speech recognition, natural language processing, and autonomous driving.

• Popular deep learning frameworks include TensorFlow, PyTorch, and Keras.

LSTM is a type of RNN with additional memory cells to better capture long-term dependencies.

• LSTM has a more complex architecture with memory cells, input, forget, and output gates.

• RNN suffers from vanishing gradient problem, while LSTM can handle long sequences better.

• LSTM is better suited for tasks requiring long-term memory retention, such as speech recognition or language translation.