1. Tell us what is the difference between supervised and unsupervised machine learning?
Supervised learning requires training labeled data. For example, in order to do classification (a supervised learning task), you'll need to first label the data you'll use to train the model to classify data into your labeled groups. Unsupervised learning, in contrast, does not require labeling data explicitly.
2. Tell us when will you use classification over regression?
Classification is about identifying group membership while regression technique involves predicting a response. Both techniques are related to prediction, where classification predicts the belonging to a class whereas regression predicts the value from a continuous set. Classification technique is preferred over regression when the results of the model need to return the belongingness of data points in a dataset to specific explicit categories. (For instance, when you want to find out whether a name is male or female instead of just finding it how correlated they are with male and female names.
3. Can you name some feature extraction techniques used for dimensionality reduction?
☛ Independent Component Analysis
☛ Principal Component Analysis
☛ Kernel Based Principal Component Analysis
4. Tell me how does deep learning contrast with other machine learning algorithms?
Deep learning is an approach to machine learning wherein the system learns the model as a neural network. If we're addressing the algorithms specifically, it should be noted that deep learning algorithms learn meaningful features on their own, without requiring any manual feature selection.
5. Tell us how do bias and variance play out in machine learning?
Both bias and variance are errors. Bias is an error due to flawed assumptions in the learning algorithm. Variance is an error resulting from too much complexity in the learning algorithm.
6. Tell me what are your favorite use cases of machine learning models?
The Quora thread above contains some examples, such as decision trees that categorize people into different tiers of intelligence based on IQ scores. Make sure that you have a few examples in mind and describe what resonated with you. It's important that you demonstrate an interest in how machine learning is implemented.
What's important here is to define your views on how to properly visualize data and your personal preferences when it comes to tools. Popular tools include R's ggplot, Python's seaborn and matplotlib, and tools such as Plot.ly and Tableau.
8. How would you evaluate a logistic regression model?
A subsection of the question above. You have to demonstrate an understanding of what the typical goals of a logistic regression are (classification, prediction etc.) and bring up a few examples and use cases.
9. Tell us what's the difference between a generative and discriminative model?
A generative model will learn categories of data while a discriminative model will simply learn the distinction between different categories of data. Discriminative models will generally outperform generative models on classification tasks.
10. Tell me how a ROC curve works?
The ROC curve is a graphical representation of the contrast between true positive rates and the false positive rate at various thresholds. It's often used as a proxy for the trade-off between the sensitivity of the model (true positives) vs the fall-out or the probability it will trigger a false alarm (false positives).
11. Tell me what is the most frequent metric to assess model accuracy for classification problems?
Percent Correct Classification (PCC) measures the overall accuracy irrespective of the kind of errors that are made, all errors are considered to have same weight.
12. Explain me machine learning in to a layperson?
Machine learning is all about making decisions based on previous experience with a task with the intent of improving its performance. There are multiple examples that can be given to explain machine learning to a layperson –
☛ Imagine a curious kid who sticks his palm
☛ You have observed from your connections that obese people often tend to get heart diseases thus you make the decision that you will try to remain thin otherwise you might suffer from a heart disease. You have observed a ton of data and come up with a general rule of classification.
☛ You are playing blackjack and based on the sequence of cards you see, you decide whether to hit or to stay. In this case based on the previous information you have and by looking at what happens, you make a decision quickly.
In inductive machine learning, the model learns by examples from a set of observed instances to draw a generalized conclusion whereas in deductive learning the model first draws the conclusion and then the conclusion is drawn. Let's understand this with an example, for instance, if you have to explain to a kid that playing with fire can cause burns. There are two ways you can explain this to kids, you can show them training examples of various fire accidents or images with burnt people and label them as “Hazardous”. In this case the kid will learn with the help of examples and not play with fire. This is referred to as Inductive machine learning. The other way is to let your kid play with fire and wait to see what happens. If the kid gets a burn they will learn not to play with fire and whenever they come across fire, they will avoid going near it. This is referred to as deductive learning.
14. Tell us how do classification and regression differ?
Classification predicts group or class membership. Regression involves predicting a response. Classification is the better technique when you need a more definite answer.
15. Explain me what is machine learning?
In answering this question, try to show your understand of the broad applications of machine learning, as well as how it fits into AI. Put it into your own words, but convey your understanding that machine learning is a form of AI that automates data analysis to enable computers to learn and adapt through experience to do specific tasks without explicit programming.
16. Tell me what are the last machine learning papers you've read?
Keeping up with the latest scientific literature on machine learning is a must if you want to demonstrate interest in a machine learning position. This overview of deep learning in Nature by the scions of deep learning themselves (from Hinton to Bengio to LeCun) can be a good reference paper and an overview of what's happening in deep learning - and the kind of paper you might want to cite.
A hash table is a data structure that produces an associative array. A key is mapped to certain values through the use of a hash function. They are often used for tasks such as database indexing.
You would first split the dataset into training and test sets, or perhaps use cross-validation techniques to further segment the dataset into composite sets of training and test sets within the data. You should then implement a choice selection of performance metrics. You could use measures such as the F1 score, the accuracy, and the confusion matrix. What's important here is to demonstrate that you understand the nuances of how a model is measured and how to choose the right performance measures for the right situations.
19. Explain me how would you handle an imbalanced dataset?
An imbalanced dataset is when you have, for example, a classification test and 90% of the data is in one class. That leads to problems: an accuracy of 90% can be skewed if you have no predictive power on the other category of data! Here are a few tactics to get over the hump:
1- Collect more data to even the imbalances in the dataset.
2- Resample the dataset to correct for imbalances.
3- Try a different algorithm altogether on your dataset.
What's important here is that you have a keen sense for what damage an unbalanced dataset can cause, and how to balance that.
20. Tell us how is a decision tree pruned?
Pruning is what happens in decision trees when branches that have weak predictive power are removed in order to reduce the complexity of the model and increase the predictive accuracy of a decision tree model. Pruning can happen bottom-up and top-down, with approaches such as reduced error pruning and cost complexity pruning.
Reduced error pruning is perhaps the simplest version: replace each node. If it doesn't decrease predictive accuracy, keep it pruned. While simple, this heuristic actually comes pretty close to an approach that would optimize for maximum accuracy.
21. Explain me what's the trade-off between bias and variance?
Bias is error due to erroneous or overly simplistic assumptions in the learning algorithm you're using. This can lead to the model underfitting your data, making it hard for it to have high predictive accuracy and for you to generalize your knowledge from the training set to the test set.
Variance is error due to too much complexity in the learning algorithm you're using. This leads to the algorithm being highly sensitive to high degrees of variation in your training data, which can lead your model to overfit the data. You'll be carrying too much noise from your training data for your model to be very useful for your test data.
The bias-variance decomposition essentially decomposes the learning error from any algorithm by adding the bias, the variance and a bit of irreducible error due to noise in the underlying dataset. Essentially, if you make the model more complex and add more variables, you'll lose bias but gain some variance - in order to get the optimally reduced amount of error, you'll have to tradeoff bias and variance. You don't want either high bias or high variance in your model.
22. Explain me what cross-validation technique would you use on a time series dataset?
Instead of using standard k-folds cross-validation, you have to pay attention to the fact that a time series is not randomly distributed data - it is inherently ordered by chronological order. If a pattern emerges in later time periods for example, your model may still pick up on it even if that effect doesn't hold in earlier years!
You'll want to do something like forward chaining where you'll be able to model on past data then look at forward-facing data.
fold 1 : training [1], test [2]
fold 2 : training [1 2], test [3]
fold 3 : training [1 2 3], test [4]
fold 4 : training [1 2 3 4], test [5]
fold 5 : training [1 2 3 4 5], test [6]
23. Tell us which one would you prefer to choose – model accuracy or model performance?
Model accuracy is just a subset of model performance but is not the be-all and end-all of model performance. This question is asked to test your knowledge on how well you can make a perfect balance between model accuracy and model performance.
If accuracy is a major concern for you when deciding on a machine learning algorithm then the best way to go about it is test a couple of different ones (by trying different parameters within each algorithm ) and choose the best one by cross-validation. A general rule of thumb to choose a good enough machine learning algorithm for your classification problem is based on how large your training set is. If the training set is small then using low variance/high bias classifiers like Naïve Bayes is advantageous over high variance/low bias classifiers like k-nearest neighbour algorithms as it might overfit the model. High variance/low bias classifiers tend to win when the training set grows in size.
25. Please explain what is deep learning?
This might or might not apply to the job you're going after, but your answer will help to show you know more than just the technical aspects of machine learning. Deep learning is a subset of machine learning. It refers to using multi-layered neural networks to process data in increasingly complex ways, enabling the software to train itself to perform tasks like speech and image recognition through exposure to these vast amounts of data. Thus the machine undergoes continual improvement in the ability to recognize and process information. Layers of neural networks stacked on top of each for use in deep learning are called deep neural networks.
