A collection of technical interview questions for computer vision engineering positions.
1) What's the trade-off between bias and variance? [src]
If our model is too simple and has very few parameters then it may have high bias and low variance. On the other hand if our model has large number of parameters then it’s going to have high variance and low bias. So we need to find the right/good balance without overfitting and underfitting the data. [src]
2) What is gradient descent? [src]
3) Explain over- and under-fitting and how to combat them? [src]
4) How do you combat the curse of dimensionality? [src]
- Manual Feature Selection
- Principal Component Analysis (PCA)
- Multidimensional Scaling
- Locally linear embedding
[src]
5) What is regularization, why do we use it, and give some examples of common methods? [src]
A technique that discourages learning a more complex or flexible model, so as to avoid the risk of overfitting. Examples
- Ridge (L2 norm)
- Lasso (L1 norm)
The obvious disadvantage of ridge regression, is model interpretability. It will shrink the coefficients for least important predictors, very close to zero. But it will never make them exactly zero. In other words, the final model will include all predictors. However, in the case of the lasso, the L1 penalty has the effect of forcing some of the coefficient estimates to be exactly equal to zero when the tuning parameter λ is sufficiently large. Therefore, the lasso method also performs variable selection and is said to yield sparse models. [src]
6) Explain Principal Component Analysis (PCA)? [src]
7) Why is ReLU better and more often used than Sigmoid in Neural Networks? [src]
Imagine a network with random initialized weights ( or normalised ) and almost 50% of the network yields 0 activation because of the characteristic of ReLu ( output 0 for negative values of x ). This means a fewer neurons are firing ( sparse activation ) and the network is lighter. [src]
8) Given stride S and kernel sizes for each layer of a (1-dimensional) CNN, create a function to compute the receptive field of a particular node in the network. This is just finding how many input nodes actually connect through to a neuron in a CNN. [src]
9) Implement connected components on an image/matrix. [src]
10) Implement a sparse matrix class in C++. [src]
11) Create a function to compute an integral image, and create another function to get area sums from the integral image.[src]
12) How would you remove outliers when trying to estimate a flat plane from noisy samples? [src]
14) How does image registration work? Sparse vs. dense optical flow and so on. [src]
15) Describe how convolution works. What about if your inputs are grayscale vs RGB imagery? What determines the shape of the next layer? [src]
16) Talk me through how you would create a 3D model of an object from imagery and depth sensor measurements taken at all angles around the object. [src]
17) Implement SQRT(const double & x) without using any special functions, just fundamental arithmetic. [src]
18) Reverse a bitstring. [src]
19) Implement non maximal suppression as efficiently as you can. [src]
20) Reverse a linked list in place. [src]
21) What is data normalization and why do we need it? [src]
Data normalization is very important preprocessing step, used to rescale values to fit in a specific range to assure better convergence during backpropagation. In general, it boils down to subtracting the mean of each data point and dividing by its standard deviation. If we don't do this then some of the features (those with high magnitude) will be weighted more in the cost function (if a higher-magnitude feature changes by 1%, then that change is pretty big, but for smaller features it's quite insignificant). The data normalization makes all features weighted equally.
22) Why do we use convolutions for images rather than just FC layers? [src]
Firstly, convolutions preserve, encode, and actually use the spatial information from the image. If we used only FC layers we would have no relative spatial information. Secondly, Convolutional Neural Networks (CNNs) have a partially built-in translation in-variance, since each convolution kernel acts as it's own filter/feature detector.
23) What makes CNNs translation invariant? [src]
As explained above, each convolution kernel acts as it's own filter/feature detector. So let's say you're doing object detection, it doesn't matter where in the image the object is since we're going to apply the convolution in a sliding window fashion across the entire image anyways.
24) Why do we have max-pooling in classification CNNs? [src]
for a role in Computer Vision. Max-pooling in a CNN allows you to reduce computation since your feature maps are smaller after the pooling. You don't lose too much semantic information since you're taking the maximum activation. There's also a theory that max-pooling contributes a bit to giving CNNs more translation in-variance. Check out this great video from Andrew Ng on the benefits of max-pooling.
25) Why do segmentation CNNs typically have an encoder-decoder style / structure? [src]
The encoder CNN can basically be thought of as a feature extraction network, while the decoder uses that information to predict the image segments by "decoding" the features and upscaling to the original image size.
Contributions are most welcomed.
- Fork the repository.
- Commit your questions or answers.
- Open pull request.
