SMS

.docx

School

Seneca College *

*We aren’t endorsed by this school

Course

315

Subject

Computer Science

Date

Jun 21, 2024

Type

docx

Pages

3

Uploaded by CoachFreedomWolverine30

SMS 416 Question 1 Assume that, for the same price The power of the CPU will double every 18 months, The power of disk will double every 12 months, The power of the network connectivity will double every 9 months and The power of the software will double every 6 months Also assume that the computer power increase is measured by the product of the increase of these four factors. Calculate the growth of the computing power after 6 years. Step 1: Converting months to years CPU – Doubles every 18 months or every 1.5 years Disk – Doubles every 12 months or every 1 years Network Connectivity – Doubles every 9 months or every 0.75 years Software – Doubles every 6 months or every 0.5 years Step 2: Annual Growth Rate CPU – 2^(1/1.5) = 1.587 Disk – 2^(1/1) = 2 Network Connectivity – 2^(1/0.75) = 2.520 Software – 2^(1/0.5) = 4 Step 3: Calculating the growth in 6 years (1 dollar initial value) CPU – (1.587^6)*1 = 16 Disk – (2^6)*1= 64 Network Connectivity – (2.52^6)*1 = 256 Software – (4^6)*1 = 4096 Step 4: Combined Growth 16*64*256*4096 = 1,073,741,824
Question 2 Identify which type of data analytics each of the following applications belongs to. The four types of analytics are: 1. Diagnostic analytics 2. Descriptive Analytics 3. Predictive Analytics 4. Prescriptive Analytics Application Sales Forecasting – Predictive Analytics Analyzing the reasons why the wars in the Middle East and Ukraine are happening concurrently – Diagnostic Analytics Website traffic analysis and heat maps – Descriptive Analytics Analyzing the actions to be taken to stop bad behavior of employees in a company – Prescriptive Analytics Question 3 In the above diagram of a simple feed-forward neural network, assume that every node is implemented using a simple “perceptron” without any looping mechanisms (like the one we discussed in the class). If the training of this network is to be done by solving a non-linear multi- variate regression model with five inputs and four outputs, how many variables would need to be determined in the model to solve the regression problem (train the neural network)? Please show your calculations. 5*7 + 7*7 + 7*4 = 112 7+7+4 = 21 112+21 = 133 Question 4 Netflix – one sided network effects , as more users joined the platform, the company could buy more content
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help