Machine Learning Engineer Interview Questions

Guilherme F. - "A much better solution than the one in the article, below: It looks like the ones writing articles here in Javascript do not understand the time/space complexity of javascript methods. shift, splice, sort, etc... In the solution article you have a shift and a sort being done inside a while, that is, the multiplication of Ns. My solution, below, iterates through the list once and then sorts it, separately. It´s O(N+Log(N)) class ListNode { constructor(val = 0, next = null) { th"See full answer

Anonymous Condor - "Yes, I need to compare the first half of the first string with the reverse order of the second half of the second string. Repeat this process to the first half of the second string and the second half of the first string."See full answer

Surbhi G. - "Deep Learning is a part of Artificial Intelligence, it's like teaching the machine to think and make decisions on its own. It's like how we teach a child the concept of an apple - it's round, red, has a stem on top. We show them multiple pictures of apples and then they understand and can recognize an apple in future. Similarly, we feed lots of data to the machine, and slowly, it starts learning from that data, and can then make relevant predictions or decisions based on what it has learnt. A co"See full answer

Constantin P. - "Reinforcement Learning is a type of machine learning where an agent learns to make decisions by trying out different actions and receiving rewards or penalties in return. The goal is to learn, over time, which actions yield the highest rewards. There are three core components in RL: The agent — the learner or decision-maker (e.g., an algorithm or robot), The environment — everything the agent interacts with, Actions and rewards — the agent takes actions, and the environmen"See full answer

Rick E. - " O(n) time, O(1) space from typing import List def maxsubarraysum(nums: List[int]) -> int: if len(nums) == 0: return 0 maxsum = currsum = nums[0] for i in range(1, len(nums)): currsum = max(currsum + nums[i], nums[i]) maxsum = max(currsum, max_sum) return max_sum debug your code below print(maxsubarraysum([-1, 2, -3, 4])) `"See full answer

Ban N. - "Follow news and resources via conferences or top companies' blogs, such as NeurIPS 2023 or Google Research Blog to get updates about the machine learning landscape. Research the papers on the new technology or approach that was mentioned or introduced via the subscribed sources, such as listed above. Following media channels, podcasts, or influencers on social media who were recently active in the industry to catch up with the trending and valuable insights, research, thoughts... Scan Github"See full answer

L B. - "For data distribution drift: DL Divergence or PSI (Population Stability Index) performance: two categories: 1st operational metrics: runtime. 2nd model performance: loss function, MAE (regression), business metrics: overall watch time, DAU, revenue lift etc Outlier: data distribution"See full answer