IBM study P3

What are the possible values of the dependent variable in a sigmoid operation?

A) Any value between 0 and 1.

All learned knowledge is uncertain and learning itself is a form of concert in inference. The problem then becomes how to deal with nosy incomplete and even contradictory information, without falling apart. The solution is probabilistic inference, and the algorithm is...?

A) Bayes theorem.

When predicting future grades based on past performance that had "hours sleep" and "hours studying" as dependent variable, why was there need to normalize hours and grades?

A) Because that would be like comparing apples to oranges.

In a convolutional neural network, three are many layers such, s input, layer pooling, ReLU and so forth. The connection from one layer to another layer is done using programmatic "synapses", which contain the "weights". What do the nodes inside the hidden layers contain?

A) Bias.

In the example of Water flowing into a target, the flow rate of water is akin to the...and the volume of water in the tank is akin to...?

A) Derivative, Integral.

[Select all that apply]. Which of the given examples are perfect scenarios for machine learning systems?

A) Humans are unable to explain their expertise. & B) Solution changes with time. & C) Solution needs to be adapted to particular cases.

What is meant by gradient descent in a neural network?

A) In machine learning, it's typically used to minimize the error function.

The Project Debater uses....that allow it to find arguments to support the general human dilemmas that are rise by the debate tonic.?

A) Knowledge graph

How would you categorize Watson the Jeopardy! Game winner in 2011 with regard to the level of artificial intelligence it played?

A) Narrow Artificial Intelligence

Applying bias, such as a sigmoid operation or ReLU and a host of other algorithms, takes place in which particular construct of a neural network?

A) Node

With machine learning algorithms that use gradient descent, the idea is to use use...to find the downward slope?

A) Partial derivatives.

In a neural network, changes to the weight alter the steepness of the vector or curve. The bias, on the other hand....

A) Shifts the entire vector

Derivatives and Integrals are used often with machine learning algorithms. Given that derivatives and integrals are opposite of each other, and since we measure surface and under a curve by integrals, then what do derivatives measure?

A) Slope

A single perceptron can solve a linear problem, then additional perceptrons give a network the ability to...?

A) Solve non-linear problems

Which of the following would constitute a deep learning framework?

A) TensorFlow

The first step in Project Debater is to build on creating speech to defend of pose the motion. Project Debater researches for short pieces of text the massive pronate at can service this purpose. Which of the following activities brings forth the power of AI in Project Debater?

A) To understand human l

With AI systems...if the process of defining an algorithm so it can learn from a data set. The output of mis operation is called a model. A model encompasses the learning coefficient of mathematical expression.

A) Training.

Statisticians often refer to allowing something in exchange for reducing variance. Which of the following depicts what statisticians are referring to?

A) Unlike regression, machine learning predictions might be wrong on average, but when the predictions miss, they often don't miss by much.

Given that the X-axis independent variable contains the area in sq are feet of houses, and Y-axis contains the corresponding sale price of those house, which of the following approaches would you use to predict the house prices as the square footage increase?

A) linear regression.

Which of the following is an example of object localization used with visual recognition?

B) Bounding Box

If the grading system was such that your grades were presented as A, A-, B+ and so forth (each encompasses an integer number; for example, A is anything from 93 up to maximum of 100), which of the following will be the appropriate approach to your data analysis?

B) Classification problem

Supervised learning has many advantages. Which of the following may be some shortcomings of supervises warning?

B) Labeling the data is arduous and expensive.

Let's say you are asked with climbing to the top of a hill, dfolded and requires to do so in as few steps as possible. In machine learning parlance, what would the slope be called?

B) Learning Rate

Let's say you are tasked with climbing blind fold on the top of a hill and required to do so in a few steps as possible. In machine learning practice, what would the slop of this hill (curve) be?

B) Learning Rate

Let's say you want to predict how much salary on would each based on level of education. Your Y axis is salary and your X axis is educational bucket (high school, Bachelors, Masters, and so forth). Which of the following models is best suited to help you predict, given a certain salary, what might the education level of the individual be?

B) Linear regression

Which of the following approaches you would use if you wanted to predict, based on size, whether a house could sell for more than $200K. Taking into consideration that the possible outputs are either "Yes", the house will sell for more than $200K, or "No", the house will not.?

B) Logistical Regression

Linear regression tries to fit a line, vnre...the distance to each data point?

B) Minimizing.

The Watson Jeopardy games used....machine learning?

B) Supervised.

Assigning an image to one or more categories, is different from assigning a single word to that image. The term often used to indicate assigning word(s) to an image is known as:

B) Tagging.

Decision trees support vector machines, and Naïve Bate are different techniques to solve a...problem.

C) Classification.

The basic building block in a neural network is called a perceptron. Which of the following best describes the role of perceptron?

C) It takes an input and produces an output value that is governed by an activation function.

Training a regular network is often characterized as:

C) Minimizing cost function.

Ethics is becoming major trust issues in the AI development. As an example, bias has to do with a prejudice in favor or against something and in practice it can lead someone to behave unfairly toward a certain group compared to others. Which of the following is an example of a blatant bias in current AI systems?

C) System recognizing age attributed on dark skinned female faces.

In a convolutional neural network with many layers, when images are uploaded to the system, what do the first layers perform?

C) The first layers identify edges in the images.

Which of the following events is distinctly in the realm of general AI and not a capability of today's artificial intelligence?

C) use previous experiences to come up with new creative ideas.

Which of the following functions as an example of deterministic systems?

D) Force = mass x acceleration (F=ma)

What makes a deep learning network deep?

D) It is a multi-layer perceptron with many 'hidden' layers.

What is the name of this curve?

D) Sigmoid operation.

Re-enforcement learning is a machine learning algorithm that is less suited for which of the following tasks?

D) Stocking, as well as retrieving, products in the warehouse for optimizing space utilization and warehouse operations.

Which of the following algorithms is used for supervised learning?

D) Support Vector Machines.

When using the gradient descent algorithm, the gradient, or slope of the descent' is also referred to as the...?

D) learning Rate