Reference no: EM1317150
Company hires your team in order to develop the back-propagation neural network(s) for predicting next-week trend of five stocks (that is, go up, go down, or remain same). In meantime, company also offers you the data for every stock in past 15 years. Every data record comprises of 20 attributes (like revenues, index values, earnings per share, capital investment, etc). Provide answer for the following questions:
1) The team member A proposes that you must design a single neural network which can handle all these stocks. However, member B allows that you have to design five networks (one for each stock). Whom do you consider as correct and also explain why?
2) During training, at a certain point, you recognizes that the error rate (of each training cycle) has been oscillating (that is it reduces in the round n, increases in the round n+1, and decreases again inround n+2, and so on). What might be the reason for this phenomenon and what you should do about it?
3) Supposing you carefully trained the network or networks with all the 10 attributes of data objects for 20,000 cycles ((i.e., epochs) and never observed any oscillation. The total error rate has been reducing all the time till a very, very small value. Thus, everything looks great. Though, when you tested the network(s) along with a new testing data set (or new testing data sets), the outcomes of neural network(s) were very bad (low accuracy). Provide at least two possible reasons and how to prevent them?
4) Explain why utilizing the maximum number of the training epochs or maximum acceptable errors in each epoch as termination condition for BP network training would be problematic? Explain the problem that such termination conditions may result in?
|
Insert the missing code in the c program
: You are to insert the missing code in the C program given for combinational equivalence checking. This program will interface with the CUDD package and will parse netlist files in ISCAS85 circuit format. Next, BDDs will be created for each circuit an..
|
|
Prepare adjusting entry and find balance in prepaid rent
: Prepare the adjusting entry for December 31 st to reflect the amount of rent expense consumed. What is balance in prepaid rent on December 31 st after the adjusting entry has been made?
|
|
Finding total cost-total revenue and profit
: For monthly volume of 300 tables, find out total cost, total revenue and profit.
|
|
Conclusion of mean waiting time
: At the .05 significance level, can we conclude that the mean waiting time is less than 3 minutes?
|
|
Back-propagation neural network
: Company hires your team in order to develop the back-propagation neural network(s) for predicting next-week trend of five stocks (that is, go up, go down, or remain same).
|
|
Describe the use of nuclear isotope
: Explain the use of nuclear isotope in medical field and Write a paragraph expaining what nuclear isotope can be used for medical purpose
|
|
Amount of accumulated depreciation and current ratio
: A company has current assets of $45,000, current liabilities of $30,000, and total liabilities of $55,000. The current ratio is:
|
|
India and china are recognized as emerging asian powers
: India and China are recognized as emerging Asian powers, especially in the area of international outsourcing. Choose one of the two countries and explain why this is occurring. Address what is driving this trend, to include the educational system, p..
|
|
Interpreting coefficient on log
: Interpret coefficient on log (salesm). If salesm were to be increased by 20%, what would be estimated change in mktgp? Would this effect be substantive?
|