Filter interviews by
I applied via LinkedIn and was interviewed in Apr 2020. There were 3 interview rounds.
Adam optimizer is an extension to the Gradient Descent optimizer with adaptive learning rates and momentum.
Adam optimizer combines the benefits of both AdaGrad and RMSProp optimizers.
Adam optimizer uses adaptive learning rates for each parameter.
Gradient Descent optimizer has a fixed learning rate for all parameters.
Adam optimizer includes momentum to speed up convergence.
Gradient Descent optimizer updates parameters b...
Use ReLU for hidden layers in deep neural networks, avoid for output layers.
ReLU is commonly used in hidden layers to introduce non-linearity and speed up convergence.
Avoid using ReLU in output layers for regression tasks as it can lead to vanishing gradients.
Consider using Leaky ReLU or Sigmoid for output layers depending on the task.
ReLU is computationally efficient and helps in preventing the vanishing gradient prob...
I applied via Company Website and was interviewed in Dec 2023. There were 3 interview rounds.
Standard question from sql and python in hackerrank
Reverse a linked list by changing the direction of pointers
Start with three pointers: current, previous, and next
Iterate through the linked list, updating pointers to reverse the direction
Return the new head of the reversed linked list
I applied via Approached by Company and was interviewed in Aug 2023. There was 1 interview round.
Logistic regression can be applied for multiclasstext classification by using one-vs-rest or softmax approach.
One-vs-rest approach: Train a binary logistic regression model for each class, treating it as the positive class and the rest as the negative class.
Softmax approach: Use the softmax function to transform the output of the logistic regression into probabilities for each class.
Evaluate the model using appropriate...
I applied via Referral and was interviewed before May 2023. There were 4 interview rounds.
180 mins of online test with camera ON. Major topics include Excel, Aptitude, Python, Statistics and Case Study
Apriori method is a popular algorithm for frequent itemset mining in data mining.
Used for finding frequent itemsets in transactional databases
Based on the concept of association rule mining
Involves generating candidate itemsets and pruning based on support threshold
Example: If {milk, bread} is a frequent itemset, then {milk} and {bread} are also frequent
Train-test split is a method used to divide a dataset into training and testing sets for model evaluation in Scikit learn.
Split the dataset into two subsets: training set and testing set
Training set is used to train the model, while testing set is used to evaluate the model's performance
Common split ratios are 70-30 or 80-20 for training and testing sets
Example: X_train, X_test, y_train, y_test = train_test_split(X, y,
I applied via LinkedIn and was interviewed before Apr 2023. There was 1 interview round.
fbprophet is a forecasting model developed by Facebook that uses time series data to make predictions.
fbprophet is an open-source forecasting tool developed by Facebook's Core Data Science team.
It is based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects.
fbprophet can be used to forecast traffic by providing historical data on traffic patterns and usi...
Technical Support Engineer
163
salaries
| ₹4.4 L/yr - ₹17 L/yr |
Senior Software Engineer
109
salaries
| ₹15 L/yr - ₹42 L/yr |
Senior Technical Support Engineer
77
salaries
| ₹10.9 L/yr - ₹25 L/yr |
Software Engineer2
67
salaries
| ₹13.4 L/yr - ₹30 L/yr |
Software Engineer
58
salaries
| ₹9.9 L/yr - ₹29.5 L/yr |
VMware Software
Microsoft Corporation
IBM
Oracle