"Clarify
"What do you mean by favorite product? Are you thinking specifically hardware, software, or a feature within those, or something non-electronic? Dealer's Choice.
"Are you asking why I love this product, or to explain why this product is a market leader independent of how i feel about it? Talk about why YOU love this product.
Rephrase Question
With all that in mind, i want to rephrase the question. "What is your favorite software product and what features in this product"
Tim W. - "Clarify
"What do you mean by favorite product? Are you thinking specifically hardware, software, or a feature within those, or something non-electronic? Dealer's Choice.
"Are you asking why I love this product, or to explain why this product is a market leader independent of how i feel about it? Talk about why YOU love this product.
Rephrase Question
With all that in mind, i want to rephrase the question. "What is your favorite software product and what features in this product"See full answer
"To handle the non-uniform sampling, I'd first clean and divide the dataset into chunks of n second interval 'uniform' trajectory data(e.g. 5s or 10s trajectories). This gives us a cleaner trajectory data chunks, T, of format (ship_ID, x, y, z, timestamp) to be formed.
For the system itself, I'd use a generative model, e.g. Variational AutoEncoder (VAE), and train the model's 'encoder' to produce a latent-space representation of input features (x,y,z,timestamp) from T, and it's 'decoder' to pred"
Anonymous Hornet - "To handle the non-uniform sampling, I'd first clean and divide the dataset into chunks of n second interval 'uniform' trajectory data(e.g. 5s or 10s trajectories). This gives us a cleaner trajectory data chunks, T, of format (ship_ID, x, y, z, timestamp) to be formed.
For the system itself, I'd use a generative model, e.g. Variational AutoEncoder (VAE), and train the model's 'encoder' to produce a latent-space representation of input features (x,y,z,timestamp) from T, and it's 'decoder' to pred"See full answer
"[I'm not sure whether the answer below is the best, as I have not gotten result and feedback from my interview]
Ans: I would solve by first using a VAE-style model, to create a latent space embedding that translates user description to generate images. Training would be done on the 1000 avatar images and 100000 descriptions, following this scheme:
VAE:
description -> encoder -> latent space -> decoder -> image
Q: "OK, but that means you're limiting the generated images to be only the 1000 imag"
Nick S. - "[I'm not sure whether the answer below is the best, as I have not gotten result and feedback from my interview]
Ans: I would solve by first using a VAE-style model, to create a latent space embedding that translates user description to generate images. Training would be done on the 1000 avatar images and 100000 descriptions, following this scheme:
VAE:
description -> encoder -> latent space -> decoder -> image
Q: "OK, but that means you're limiting the generated images to be only the 1000 imag"See full answer
"The correct answer as per the interviewer was since we have to exclude in build product engagement metrics and user feedback for the sake of this question, consulting firms/data analytics firms who do market research we rely on that data to determine how useful a competitor's feature is . again this is the answer provided by the interviewer."
Manas M. - "The correct answer as per the interviewer was since we have to exclude in build product engagement metrics and user feedback for the sake of this question, consulting firms/data analytics firms who do market research we rely on that data to determine how useful a competitor's feature is . again this is the answer provided by the interviewer."See full answer