Deep Learning with Keras Interview Questions

Deep Learning with Keras

Keras is an open-source neural-network library written in Python. Do refer these interview questions to prepare yourself for next job role in data science.

Q.15 Explain the examples of data processing in Keras.

Some of the examples include: Firstly, neural networks don't process raw data, like text files, encoded JPEG image files, or CSV files. They process vectorized & standardized representations. Secondly, text files need to be read into string tensors, then split into words. Finally, the words need to be indexed and turned into integer tensors. Thirdly, images need to be read and decoded into integer tensors, then converted to floating points and normalized to small values (usually between 0 and 1). Lastly, CSV data needs to be parsed, with numerical features converted to floating-point tensors and categorical features indexed and converted to integer tensors. Then each feature typically needs to be normalized to zero-mean and unit variance.

Q.19 What is Long Short Term Memory (LSTM)? Explain its process.

LSTM’s have a Nature of Remembering information for long periods of time is their Default behavior. The LSTM had a three-step Process:

1. Forget Gate This gate Decides which information is to be omitted from the cell in that particular timestamp. It is decided by the sigmoid function. However, it looks at the previous state(ht-1) and the content input(Xt) and outputs a number between 0(omit this)and 1(keep this)for each number in the cell state Ct−1.

2. Update Gate/input gate Decides how much of this unit is added to the current state. In this, the Sigmoid function decides which values to let through 0,1. and tanh function gives weightage to the values which are passed deciding their level of importance ranging from-1 to 1.

3. Output Gate Decides which part of the current cell makes it to the output. In this, the Sigmoid function decides which values to let through 0,1. and tanh function gives weightage to the values which are passed deciding their level of importance ranging from-1 to 1 and multiplied with an output of Sigmoid.

Q.25 Explain the L2 and L1 Regularization techniques.

L2 and L1 are the most common types of regularization. Regularization works on the premise that smaller weights lead to simpler models which result helps in avoiding overfitting. So to obtain a smaller weight matrix, these techniques add a ‘regularization term’ along with the loss to obtain the cost function. Here, Cost function = Loss + Regularization term However, the difference between L1 and L2 regularization techniques lies in the nature of this regularization term. In general, the addition of this regularization term causes the values of the weight matrices to reduce, leading to simpler models.

Q.27 What do you understand about Dropout and early stopping techniques?

Dropout means that during the training, randomly selected neurons are turned off or ‘dropped’ out. It means that they are temporarily obstructed from influencing or activating the downward neuron in a forward pass, and none of the weights updates is applied on the backward pass. Whereas Early Stopping is a kind of cross-validation strategy where one part of the training set is used as a validation set, and the performance of the model is gauged against this set. So if the performance on this validation set gets worse, the training on the model is immediately stopped. However, the main idea behind this technique is that while fitting a neural network on training data, consecutively, the model is evaluated on the unseen data or the validation set after each iteration. So if the performance on this validation set is decreasing or remaining the same for certain iterations, then the process of model training is stopped.

Q.31 Explain the process of training a CNN.

The process for training a CNN for classifying images consists of the following steps −

1. Data Preparation In this step, we center-crop the images and resize them so that all images for training and testing would be of the same size. This is usually done by running a small Python script on the image data.

2. Model Definition In this step, we define a CNN architecture. The configuration is stored in .pb (protobuf) file.

3. Solver Definition In this, we define the solver configuration file. The solver does the model optimization.

4. Model Training In this, we use the built-in Caffe utility to train the model. The training may take a considerable amount of time and CPU usage. After the training is completed, Caffe stores the model in a file, which can, later on, be used on test data and final deployment for predictions.

Q.37 Explain the process of debugging your model with eager execution.

If you write custom training steps or custom layers, you will need to debug them. The debugging experience refers to an integral part of a framework and with Keras, the debugging workflow is designed with the user in mind. However, by default, Keras models are compiled to highly optimized computation graphs that deliver fast execution times. That means that the Python code you write is not the code you are actually executing. This introduces a layer of indirection that can make debugging hard. Further, it is better to perform debugging in a step-by-step manner. You want to be able to sprinkle your code with a print() statement to see what your data looks like after every operation, you want to be able to use pdb. You can achieve this by running your model eagerly. With eager execution, the Python code you write is the code that gets executed. Simply pass run_eagerly=True to compile():

Q.47 Define the following terms: TensorFlow Cloud, TensorFlow.js and TensorFlow Lite.

TensorFlow Cloud is managed by the Keras team at Google that refers to a set of utilities to help you run large-scale Keras training jobs on GCP with very little configuration effort. Running your experiments on 8 or more GPUs in the cloud should be as easy as calling model.fit(). TensorFlow.js is TensorFlow's JavaScript runtime, capable of running TensorFlow models in the browser or on a Node.js server, both for training and inference. It natively supports loading Keras models, including the ability to fine-tune or retrain your Keras models directly in the browser. TensorFlow Lite is a runtime for an efficient on-device inference that has native support for Keras models. Deploy your models on Android, iOS, or on embedded devices.

Q.53 Describe the steps for creating a deep Learning Project in Python with Keras.

1. Load Data The first step is for defining the functions and classes. In this, we will use the NumPy library to load our dataset and we will use two classes from the Keras library to define our model.

2. Define Keras Model Models in Keras are defined as a sequence of layers. Here, we will create a Sequential model and add layers one at a time until we are happy with our network architecture. However, ensure that the input layer has the right number of input features. This can be specified when creating the first layer with the input_dim argument and setting it to 8 for the 8 input variables.

3. Compile Keras Model After defining the model, compile it. However, compiling the model uses the efficient numerical libraries under the covers (the so-called backend) such as Theano or TensorFlow. The backend automatically chooses the best way to represent the network for training and making predictions to run on your hardware, such as CPU or GPU or even distributed. During compiling, specify some additional properties required when training the network. And, also specify the loss function to use to evaluate a set of weights, the optimizer is used to search through different weights for the network and any optional metrics we would like to collect and report during training.

4. Fit Keras Model After defining and compiling it is ready for efficient computation. Now, execute the model on some data. We can train or fit our model on our loaded data by calling the fit() function on the model. However, training occurs over epochs and each epoch is split into batches. Epoch: One pass through all of the rows in the training dataset. Batch: One or more samples are considered by the model within an epoch before weights are updated. You must know that one epoch is comprised of one or more batches, depending on the chosen batch size and the model is fit for many epochs.

5. Evaluate Keras Model After training the neural network on the entire dataset and we can examine the performance of the network on the same dataset. However, we can evaluate your model on your training dataset using the evaluate() function on your model and pass it the same input and output used to train the model. Further, the evaluate() function will return a list with two values. The first will be the loss of the model on the dataset and the second will be the accuracy of the model on the dataset.

Q.61 Explain the k-Fold cross-validation technique with the algorithm.

k-Fold CV is a method that minimizes the disadvantages of the hold-out method. k-Fold introduces a new way of splitting the dataset which helps to overcome the “test only once bottleneck”. The algorithm of the k-Fold technique:

Firstly, select a number of folds – k. Usually, k is 5 or 10 but you can select any number which is less than the dataset’s length.
Secondly, divide the dataset into k equal (if possible) parts (they are called folds)
Then, select k – 1 folds which will be the training set. The remaining fold will be the test set
Fourthly, train the model on the training set. On each iteration of cross-validation, you must train a new model independently of the model trained on the previous iteration
Then, validate on the test set After that, save the result of the validation
Now, repeat steps 3 – 6 k times. Every time use the remaining fold as the test set.
In the end, you should have validated the model on every fold that you have. Lastly, for having the final score average the results that you got on step 6.

Q.63 Define Cross-Validation in Deep Learning.

Cross-validation in Deep Learning (DL) can be tricky because most of the CV techniques need training the model at least a couple of times. However, in deep learning, you would normally tempt to avoid CV because of the cost associated with training k different models. Rather than doing k-Fold or other CV techniques, you might use a random subset of your training data as a hold-out for validation purposes. For example, Keras’s deep learning library enables you to pass one of two parameters for the fit function that performs training. This covers: Firstly, validation_split: percentage of the data that should be held out for validation Secondly, validation_data: a tuple of (X, y) which should be used for validation. This parameter overrides the validation_split parameter which means you can use only one of these parameters at once. And, the same method is used in other DL frameworks such as PyTorch and MxNet. They also suggest giving the dataset into three parts: training, validation, and testing.

Q.67 What is an imbalance classification?

An imbalanced classification problem is an example of a classification problem in which the distribution of examples over the known classes is biased or skewed. The distribution can range from a slight bias to a severe imbalance where there is one example in the minority class for hundreds, thousands, or millions of examples in the majority class or classes. Further, this creates a challenge for predictive modeling as most of the machine learning algorithms used for classification were designed around the assumption of an equal number of examples for each class. This results in models that have poor predictive performance, specifically for the minority class.

Deep Learning with Keras

Get Govt. Certified

Are you an expert ?