Check out the list of top frequently asked Deep Learning Interview Questions and answers are given below.
1) What is deep learning?
Deep learning is a part of machine learning with an algorithm inspired by the structure and function of the brain, which is called an artificial neural network.
In the mid-1960s, Alexey Grigorevich Ivakhnenko published the first general, while working on deep learning network. Deep learning is suited over a range of fields such as computer vision, speech recognition, natural language processing, etc.
2) What are the main differences between AI, Machine Learning, and Deep Learning?
- AI stands for Artificial Intelligence. It is a technique which enables machines to mimic human behavior.
- Machine Learning is a subset of AI which uses statistical methods to enable machines to improve with experiences.
- Deep learning is a part of Machine learning, which makes the computation of multi-layer neural networks feasible. It takes advantage of neural networks to simulate human-like decision making.
3) Differentiate supervised and unsupervised deep learning procedures.
- Supervised learning is a system in which both input and desired output data are provided. Input and output data are labeled to provide a learning basis for future data processing.
- Unsupervised procedure does not need labeling information explicitly, and the operations can be carried out without the same. The common unsupervised learning method is cluster analysis. It is used for exploratory data analysis to find hidden patterns or grouping in data.
4) What are the applications of deep learning?
There are various applications of deep learning:
- Computer vision
- Natural language processing and pattern recognition
- Image recognition and processing
- Machine translation
- Sentiment analysis
- Question Answering system
- Object Classification and Detection
- Automatic Handwriting Generation
- Automatic Text Generation.
5) Do you think that deep network is better than a shallow one?
Both shallow and deep networks are good enough and capable of approximating any function. But for the same level of accuracy, deeper networks can be much more efficient in terms of computation and number of parameters. Deeper networks can create deep representations. At every layer, the network learns a new, more abstract representation of the input.
6) What do you mean by “overfitting”?
Overfitting is the most common issue which occurs in deep learning. It usually occurs when a deep learning algorithm apprehends the sound of specific data. It also appears when the particular algorithm is well suitable for the data and shows up when the algorithm or model represents high variance and low bias.
7) What is Backpropagation?
Backpropagation is a training algorithm which is used for multilayer neural networks. It transfers the error information from the end of the network to all the weights inside the network. It allows the efficient computation of the gradient.
Backpropagation can be divided into the following steps:
- It can forward propagation of training data through the network to generate output.
- It uses target value and output value to compute error derivative concerning output activations.
- It can backpropagate to compute the derivative of the error concerning output activations in the previous layer and continue for all hidden layers.
- It uses the previously calculated derivatives for output and all hidden layers to calculate the error derivative concerning weights.
- It updates the weights.
8) What is the function of the Fourier Transform in Deep Learning?
Fourier transform package is highly efficient for analyzing, maintaining, and managing a large databases. The software is created with a high-quality feature known as the special portrayal. One can effectively utilize it to generate real-time array data, which is extremely helpful for processing all categories of signals.
9) Describe the theory of autonomous form of deep learning in a few words.
There are several forms and categories available for the particular subject, but the autonomous pattern represents independent or unspecified mathematical bases which are free from any specific categorizer or formula.
10) What is the use of Deep learning in today’s age, and how is it adding data scientists?
Deep learning has brought significant changes or revolution in the field of machine learning and data science. The concept of a complex neural network (CNN) is the main center of attention for data scientists. It is widely taken because of its advantages in performing next-level machine learning operations. The advantages of deep learning also include the process of clarifying and simplifying issues based on an algorithm due to its utmost flexible and adaptable nature. It is one of the rare procedures which allow the movement of data in independent pathways. Most of the data scientists are viewing this particular medium as an advanced additive and extended way to the existing process of machine learning and utilizing the same for solving complex day to day issues.
11) What are the deep learning frameworks or tools?
Deep learning frameworks or tools are:
Tensorflow, Keras, Chainer, Pytorch, Theano & Ecosystem, Caffe2, CNTK, DyNetGensim, DSSTNE, Gluon, Paddle, Mxnet, BigDL
12) What are the disadvantages of deep learning?
There are some disadvantages of deep learning, which are:
- Deep learning model takes longer time to execute the model. In some cases, it even takes several days to execute a single model depends on complexity.
- The deep learning model is not good for small data sets, and it fails here.
13) What is the meaning of term weight initialization in neural networks?
In neural networking, weight initialization is one of the essential factors. A bad weight initialization prevents a network from learning. On the other side, a good weight initialization helps in giving a quicker convergence and a better overall error. Biases can be initialized to zero. The standard rule for setting the weights is to be close to zero without being too small.
14) Explain Data Normalization.
Data normalization is an essential preprocessing step, which is used to rescale values to fit in a specific range. It assures better convergence during backpropagation. In general, data normalization boils down to subtracting the mean of each data point and dividing by its standard deviation.
15) Why is zero initialization not a good weight initialization process?
If the set of weights in the network is put to a zero, then all the neurons at each layer will start producing the same output and the same gradients during backpropagation.
As a result, the network cannot learn at all because there is no source of asymmetry between neurons. That is the reason why we need to add randomness to the weight initialization process.
16) What are the prerequisites for starting in Deep Learning?
There are some basic requirements for starting in Deep Learning, which are:
- Machine Learning
- Python Programming
17) What are the supervised learning algorithms in Deep learning?
- Artificial neural network
- Convolution neural network
- Recurrent neural network
18) What are the unsupervised learning algorithms in Deep learning?
- Self Organizing Maps
- Deep belief networks (Boltzmann Machine)
- Auto Encoders
19) How many layers in the neural network?
- Input Layer
The input layer contains input neurons which send information to the hidden layer.
- Hidden Layer
The hidden layer is used to send data to the output layer.
- Output Layer
The data is made available at the output layer.
20) What is the use of the Activation function?
The activation function is used to introduce nonlinearity into the neural network so that it can learn more complex function. Without the Activation function, the neural network would be only able to learn function, which is a linear combination of its input data.
Activation function translates the inputs into outputs. The activation function is responsible for deciding whether a neuron should be activated or not. It makes the decision by calculating the weighted sum and further adding bias with it. The basic purpose of the activation function is to introduce non-linearity into the output of a neuron.
21) How many types of activation function are available?
- Binary Step
- Leaky ReLU
22) What is a binary step function?
The binary step function is an activation function, which is usually based on a threshold. If the input value is above or below a particular threshold limit, the neuron is activated, then it sends the same signal to the next layer. This function does not allow multi-value outputs.
23) What is the sigmoid function?
The sigmoid activation function is also called the logistic function. It is traditionally a trendy activation function for neural networks. The input data to the function is transformed into a value between 0.0 and 1.0. Input values that are much larger than 1.0 are transformed to the value 1.0. Similarly, values that are much smaller than 0.0 are transformed into 0.0. The shape of the function for all possible inputs is an S-shape from zero up through 0.5 to 1.0. It was the default activation used on neural networks, in the early 1990s.
24) What is Tanh function?
The hyperbolic tangent function, also known as tanh for short, is a similar shaped nonlinear activation function. It provides output values between -1.0 and 1.0. Later in the 1990s and through the 2000s, this function was preferred over the sigmoid activation function as models. It was easier to train and often had better predictive performance.
25) What is ReLU function?
A node or unit which implements the activation function is referred to as a rectified linear activation unit or ReLU for short. Generally, networks that use the rectifier function for the hidden layers are referred to as rectified networks.
Adoption of ReLU may easily be considered one of the few milestones in the deep learning revolution.