i
Blackstraw AI
Filter interviews by
I applied via Company Website and was interviewed in May 2024. There were 2 interview rounds.
Data leakage occurs when information from outside the training dataset is used to create a model, leading to unrealistic performance.
Occurs when information that would not be available in a real-world scenario is used in the model training process
Can result in overly optimistic performance metrics for the model
Examples include using future data, target leakage, and data preprocessing errors
Encoder Decoder is a neural network architecture used for sequence-to-sequence tasks. Transformer model is a type of neural network architecture that relies entirely on self-attention mechanisms.
Encoder Decoder is commonly used in machine translation tasks where the input sequence is encoded into a fixed-length vector representation by the encoder and then decoded into the target sequence by the decoder.
Transformer mod...
Deep learning models include CNN, RNN, LSTM, GAN, and Transformer.
Convolutional Neural Networks (CNN) - used for image recognition tasks
Recurrent Neural Networks (RNN) - used for sequential data like time series
Long Short-Term Memory (LSTM) - a type of RNN with memory cells
Generative Adversarial Networks (GAN) - used for generating new data samples
Transformer - used for natural language processing tasks
Regularization is a technique used in machine learning to prevent overfitting by adding a penalty term to the model's loss function.
Regularization helps to reduce the complexity of the model by penalizing large coefficients.
It adds a penalty term to the loss function, which discourages the model from fitting the training data too closely.
Common types of regularization include L1 (Lasso) and L2 (Ridge) regularization.
Re...
Model quantization is the process of reducing the precision of the weights and activations of a neural network model to improve efficiency.
Reduces memory usage and speeds up inference by using fewer bits to represent numbers
Can be applied to both weights and activations in a neural network model
Examples include converting 32-bit floating point numbers to 8-bit integers
I applied via Job Portal and was interviewed before Apr 2023. There were 2 interview rounds.
ML algorithm selection is based on data characteristics, problem type, and desired outcomes.
Understand the problem type (classification, regression, clustering, etc.)
Consider the size and quality of the data
Evaluate the complexity of the model and interpretability requirements
Choose algorithms based on their strengths and weaknesses for the specific task
Experiment with multiple algorithms and compare their performance
F...
To optimize a ML model, one can tune hyperparameters, feature engineering, cross-validation, ensemble methods, and regularization techniques.
Tune hyperparameters using techniques like grid search or random search
Perform feature engineering to create new features or select relevant features
Utilize cross-validation to evaluate model performance and prevent overfitting
Explore ensemble methods like bagging and boosting to ...
I applied via Naukri.com and was interviewed before Mar 2023. There were 3 interview rounds.
Top trending discussions
My friends think of me as reliable, supportive, and always up for a good time.
Reliable - always there when they need help or support
Supportive - willing to listen and offer advice
Fun-loving - enjoys socializing and trying new things
General aptitude basics
Mcq and basic ml model building
I applied via Approached by Company
Transformers are a type of neural network architecture that utilizes self-attention mechanisms to process sequential data.
Transformers use self-attention mechanisms to weigh the importance of different input elements, allowing for parallel processing of sequences.
Unlike RNNs and LSTMs, Transformers do not rely on sequential processing, making them more efficient for long-range dependencies.
Transformers have been shown ...
Different types of Attention include self-attention, global attention, and local attention.
Self-attention focuses on relationships within the input sequence itself.
Global attention considers the entire input sequence when making predictions.
Local attention only attends to a subset of the input sequence at a time.
Examples include Transformer's self-attention mechanism, Bahdanau attention, and Luong attention.
GPT is a generative model while BERT is a transformer model for natural language processing.
GPT is a generative model that predicts the next word in a sentence based on previous words.
BERT is a transformer model that considers the context of a word by looking at the entire sentence.
GPT is unidirectional, while BERT is bidirectional.
GPT is better for text generation tasks, while BERT is better for understanding the cont
Data scientists analyze data to gain insights, machine learning (ML) involves algorithms that improve automatically through experience, and artificial intelligence (AI) refers to machines mimicking human cognitive functions.
Data scientists analyze large amounts of data to uncover patterns and insights.
Machine learning involves developing algorithms that improve automatically through experience.
Artificial intelligence r...
I applied via Naukri.com and was interviewed in Jun 2024. There were 4 interview rounds.
First round is coding round where two use cases are there. Need to solve them
I applied via Referral and was interviewed in Sep 2024. There was 1 interview round.
Asked 2 to 3 python coding question...
I applied via Job Portal
Random forest is an ensemble learning method used for classification and regression tasks.
Random forest is a collection of decision trees that are trained on random subsets of the data.
Each tree in the random forest independently predicts the target variable, and the final prediction is made by averaging the predictions of all trees.
Random forest is robust to overfitting and noisy data, and can handle large datasets wi...
Lasso is a feature selection technique that penalizes the absolute size of the regression coefficients.
Lasso stands for Least Absolute Shrinkage and Selection Operator
It adds a penalty term to the regression equation, forcing some coefficients to be exactly zero
Helps in selecting the most important features and reducing overfitting
Useful when dealing with high-dimensional data
Example: In a dataset with multiple feature...
based on 3 interviews
Interview experience
based on 7 reviews
Rating in categories
Data Scientist
39
salaries
| ₹0 L/yr - ₹0 L/yr |
Software Engineer
35
salaries
| ₹0 L/yr - ₹0 L/yr |
Data Engineer
33
salaries
| ₹0 L/yr - ₹0 L/yr |
Software Developer
8
salaries
| ₹0 L/yr - ₹0 L/yr |
Senior Software Engineer
7
salaries
| ₹0 L/yr - ₹0 L/yr |
Fractal Analytics
Mu Sigma
Tiger Analytics
LatentView Analytics