Machine Learning: Deep Learning Questions | Practice Test / Quiz / MCQs

Home > Machine Learning 101 > Quizzes > Machine Learning: Deep Learning Questions

Machine Learning: Deep Learning Questions

Fast practice, instant feedback. Timer auto-submits when time’s up.

Avg score: 79% • Most missed: “CNN is very good with images that have:”

Deep learning is a type of machine learning, which is a subset of artificial intelligence. Machine learning is about computers being able to think and act with less human intervention; deep learning is about computers learning to think using structures modeled on the human brain.

Practical examples of deep learning are Virtual assistants, vision for driverless cars, money laundering, face recognition and many more.

Machine Learning: Deep Learning Questions

Time left 00:00

25 Questions

1. What is the architecture of GoogLeNet?

Dropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelTake a running average of derivativesA type of Neural Network layer that uses a gating mechanism to control the information flow through a layer. Stacking multiple Highway Layers allows for training of very deep networks. Highway Layers work by learning a gating function that chooses which parts of the inputs to pass through and which parts to pass through a transformation function, such as a standard affine layer for example. The basic formulation of a Highway Layer is T * h(x) + (1 - T) * x, where T is the learned gating function with values between 0 and 1, h(x) is an arbitrary input transformation and x is the input. Note that all of these must have the same size.

2. Dropout

Dropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Take a running average of derivativesNot everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelA type of Neural Network layer that uses a gating mechanism to control the information flow through a layer. Stacking multiple Highway Layers allows for training of very deep networks. Highway Layers work by learning a gating function that chooses which parts of the inputs to pass through and which parts to pass through a transformation function, such as a standard affine layer for example. The basic formulation of a Highway Layer is T * h(x) + (1 - T) * x, where T is the learned gating function with values between 0 and 1, h(x) is an arbitrary input transformation and x is the input. Note that all of these must have the same size.

3. What is momentum?

Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.A type of Neural Network layer that uses a gating mechanism to control the information flow through a layer. Stacking multiple Highway Layers allows for training of very deep networks. Highway Layers work by learning a gating function that chooses which parts of the inputs to pass through and which parts to pass through a transformation function, such as a standard affine layer for example. The basic formulation of a Highway Layer is T * h(x) + (1 - T) * x, where T is the learned gating function with values between 0 and 1, h(x) is an arbitrary input transformation and x is the input. Note that all of these must have the same size.Take a running average of derivatives

4. Highway Layer

Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelA type of Neural Network layer that uses a gating mechanism to control the information flow through a layer. Stacking multiple Highway Layers allows for training of very deep networks. Highway Layers work by learning a gating function that chooses which parts of the inputs to pass through and which parts to pass through a transformation function, such as a standard affine layer for example. The basic formulation of a Highway Layer is T * h(x) + (1 - T) * x, where T is the learned gating function with values between 0 and 1, h(x) is an arbitrary input transformation and x is the input. Note that all of these must have the same size.Dropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Take a running average of derivatives

5. Backpropagation Through Time (BPTT)

Backpropagation Through Time (paper) is the Backpropagation algorithm applied to Recurrent Neural Networks (RNNs). where each time step represents a layer and the parameters are shared across layers. Because an RNN shares the same parameters across all time steps, the errors at one time step must be backpropagated “through time” to all previous time steps. When dealing with long sequences (hundreds of inputs), a truncated version of BPTT is often used to reduce the computational cost. Truncated BPTT stops backpropagating the errors after a fixed number of steps.Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelTake a running average of derivativesDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.

6. explore-exploit dilemma

7. word2vec

Take a running average of derivativesconstructs representation of words into a vector of fixed length trained under a large corpusDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallel

8. ELU

Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelTake a running average of derivativesexponential linear unit has negative valuesDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.

9. The best neural net for images is ______.

Take a running average of derivativesCNNDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallel

10. What are RNN good at?

Take a running average of derivativeslearning sequences eg: handwriting making sentencesNot everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.

11. The best neural net for sequences is ______

RNNDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Take a running average of derivativesNot everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallel

12. How does momentum impact SGD?

Take a running average of derivativesNot everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallel'SGD with momentum remembers the update Δ w at each iteration, and determines the next update as a convex combination of the gradient and the previous update: The name momentum stems from an analogy to momentum in physics: the weight vector, thought of as a particle traveling through parameter space,[ incurs acceleration from the gradient of the loss (''force''). Unlike in classical SGD, it tends to keep traveling in the same direction, preventing oscillations.'Dropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.

13. What the region a kernel or flashlight is shining over ?

receptive fieldTake a running average of derivativesDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallel

14. How have DL networks evolved overt the last 5 years?

Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelTake a running average of derivativesMuch deeper!Dropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.

15. fine-tuning

Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelstart with a net trained on other images (e.g., ImageNet) the tune/retrain on your specific datasetDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Take a running average of derivatives

16. rmsprop

17. ANN

18. LSTMs have a sense of ______ to ______.

19. inattention valley

If a self-driving car is 50% accurate, you would always be alert and ready to take over. But 99% accurate is a problem because the driver is not ready when it’s time to take over. “We have to figure out the user interface for when the system says ‘you have to take over and I really mean it’,”Dropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelTake a running average of derivatives

20. DDN

deep directed networksDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Take a running average of derivativesNot everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallel

21. Max-Pooling

Dropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelTake a running average of derivativesselects the maximum value from a patch of features. Just like a convolutional layer, pooling layers are parameterized by a window (patch) size and stride size. For example, we may slide a window of size 2×2 over a 10×10 feature matrix using stride size 2, selecting the max across all 4 values within each window, resulting in a new 5×5 feature matrix. Pooling layers help to reduce the dimensionality of a representation by keeping only the most salient information, and in the case of image inputs, they provide basic invariance to translation (the same maximum values will be selected even if the image is shifted by a few pixels). Pooling layers are typically inserted between successive convolutional layers

22. neurons in neural nets each produce a ______________

sequence of real-valued activationsDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.Take a running average of derivativesNot everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallel

23. AdaGrad

Take a running average of derivativesadaptive gradient algorithm automatically determines a per-parameter learning rate still has a base learning rate η, but this is multiplied with the elements of a vector {Gj,j} that is thought of as the diagonal of a matrixNot everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.

24. How is the softmax layer implemented?

Take a running average of derivativesDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.The output of a neuron in a softmax layer depends on the outputs of all of the other neurons in its layer. We require the sum of all the outputs to be equal to 1. Letting zi be the logit of the ith softmax neuron, we can achieve this normalization by setting its output to:Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallel

25. ReLU

Not everything is happening sequentially, as seen in previous architectures. We have pieces of the network that are happening in parallelTake a running average of derivativesrectified linear unit an activation function defined as: Rectifier (blue) and softplus (green) functionsDropout is a regularization technique for Neural Networks that prevents overfitting. It prevents neurons from co-adapting by randomly setting a fraction of them to 0 at each training iteration. Dropout can be interpreted in various ways, such as randomly sampling from an exponential number of different networks.

⚡ Recently practiced quizzes in this topic

Live quiz activity

Machine Learning Test Machine Learning: Recommendation Systems Questions Machine Learning 101 Practice Test: Linear Regression Machine Learning Basics Knowledge Test Machine Learning 101 Practice Test: Fundamental Theorem of PAC Learning Machine Learning 101 Practice Test: Kernels And Kernel Trick Machine Learning 101 Practice Test: K-Nearest Neighbor Algorithm and Nearest Neighbor Analysis Machine Learning 101 Practice Test: Neural Networks in Machine Learning Machine Learning 101 Practice Test: Decision Trees Machine Learning 101 Practice Test: Version Spaces, Find-S Algorithm And Candidate Elimination Algorithm

25 Questions

❤ If you liked Fatskills, consider supporting us by checking out The Life Manuals You Never Got.

About | Explore | User Guide | Topics | Subjects | Doubt Solver | Career Aptitude Test | Answers | Free Tools | OSHA Basics Quiz | What Should We Know?
Privacy | Terms |

Without work one finishes nothing. - Ralph Waldo Emerson
© 2026 Fatskills.com

All trademarks, logos and brand names are the property of their respective owners. All company, product and service names used in this website are for identification purposes only. Use of these names, trademarks and brands does not imply endorsement.

25 Questions

❤ If you liked Fatskills, consider supporting us by checking out The Life Manuals You Never Got.

About | Explore | User Guide | Topics | Subjects | Doubt Solver | Career Aptitude Test | Answers | Free Tools | OSHA Basics Quiz | What Should We Know? Privacy | Terms |

Without work one finishes nothing. - Ralph Waldo Emerson© 2026 Fatskills.com

All trademarks, logos and brand names are the property of their respective owners. All company, product and service names used in this website are for identification purposes only. Use of these names, trademarks and brands does not imply endorsement.

About | Explore | User Guide | Topics | Subjects | Doubt Solver | Career Aptitude Test | Answers | Free Tools | OSHA Basics Quiz | What Should We Know?
Privacy | Terms |

Without work one finishes nothing. - Ralph Waldo Emerson
© 2026 Fatskills.com