Indian Institute of Technology Kharagpur
Asked 12th May, 2019
For learning and using Machine leaning is it necessary to have a computer science background?
I have seen interesting studies on energy which use Machine Learning algorithms. As I have a mechanical engineering background I am not sure if I can learn and use machine learning. Is it required to have a computer science background? And are the available tools for machine learning easy to use by people from other disciplines?
Most recent answer
It is not necessary to have a computer science background for learning ML. But you should know basic statistical methods and programming language. ML will definitely help you with energy forecasting.
Top contributors to discussions in this field
All Answers (6)
Dear Amirreza Heidari,
Absolutely NO.. If you know the mathematics concept, then easily you can get it. Now a days ML techniques are frequently using in all fields like civil, mechanical, computer, agriculture, etc. So no need to worry about it, any body can learn it.
I have a PhD in Mathematics and another one in Statistics. Currently I am involved in Machine Learning techniques, connected to Math and Stats, and a third PhD, in Computer Science, would come in handy! (I am too old for that, but it's not a bad idea for a younger scientist). Imagine the amount of knowldge you will have at your disposal, especially for real life applications!
Similar questions and discussions
Can you suggest a book for comprehensive understanding of controllers and working of control loops in a DC-AC converter?
- Vikas Mohan Dixit
While designing controllers for DC-AC converters, I am having difficulties in understanding the control loops for deriving a reference signal for PWM. How these loops are used with PI controllers to get desired reference signal. What is the fundamental idea behind this. Please suggest some good books and papers.
What happens if the thyristors in a TCR are fired at an angle below 90 degree ?
- Vikas Mohan Dixit
TCR consists of a linear reactor in series with anti-parallel thyristors. Firing angle in a TCR typically varies from 90 degree to 180 degree. We know that current lags the voltage by 90 degrees in a reactor. Is this the reason behind specified firing angle range or there is something else?
What happens if the TCR is fired at an angle below 90 degree?
What is the short circuit ratio(SCR) in power system? and how it is used to determine the system strength? Before answering please read description.
- Vikas Mohan Dixit
Power system strength is very important for system planning and protection design. There is one metric "SCR or short circuit ratio" generally mentioned to define the system strength. I have confusion about the definition of this index. Some texts define it as the ratio between short-circuit MVA and rated MVA and some define it in reference to the inverter based resources as the ratio between short-circuit MVA and rated MW of inverter based power source. Few references are attached.
Why would frequency change in an only inverter based power system?
- Vikas Mohan Dixit
When it comes to frequency in a power system, it is directly linked with the speed of the synchronous generator and mismatch in the mechanical input power and electrical output power accelerates or deaccelerates synchronous generator and thus frequency of the output varies, but how and why does this frequency change happen in a static inverter with load change?
Grid connected inverter using virtual synchronous machine?
- Manash Mishra
currently, I am working on the grid-connected inverter. I want to make my grid-connected PV system a PLL-less system. I have studied some reachers are implementing a virtual synchronous machine to make the system PLL-less. I have tried to implement in MATLAB SIMULINK but the grid current is distorted. Can anybody tell why this happens?
How to simulate a varying load /load profile in Simulink/MATLAB?
- Karim Aboeleneen
I am looking for a block in MATLAB that can simulate a varying load such as a load of a house given below. this block will be connected to a power system
In a single phase transformer design, the flux density of Core depends upon Voltage applied or Current drawn from it (Ampere Turns)?
- Kunal Mahajan
In a single phase transformer design, we know that-
Flux Density, B=1/(4.44*f*A*Te),
where f is the frequency, A is the cross-sectional area of the core, Te is the turn/volt value.
Hence, If we increase the voltage, flux density will also increase.
Here, there is no mention of the current drawn from the transformer secondary.
Also, we know that MMF(magnetomotive force) = N*I= ampere turns = Rm* Φ ,
where Rm is the reluctance of the core(a constant) and Φ is the flux( Φ =BA)
hence, we may conclude that Flux (also flux density, B) is directly proportional to I(current ) considering that turns, voltage , reluctance, Area of the core cross-section etc. are all constants for a given design.
Now the conflict arises that,
If the flux density, B depends on voltage across N no. of turns(as in case 1, how can it depend on the current drawn from N no. of turns?
Can anyone help me with the State Space Analysis of a three phase VSI couples with LC Filter?
- P. Arvind
What is the approach for doing the state space analysis of a three-phase VSI having LC filters coupled with each of its legs?
I want the state space analysis for each and every operating mode.
Should I consider the one-legged operation or should I take into account all the six states?
How reactive injection, change in bus voltage and short circuit level of the grid related?
- Siva Behara
By changing the reactive power in the transmission line, voltage profile also changes.
My question is, how reactive power injection into grid changes the grid voltage? and is there any relation between the grid short circuit level and reactive power injection?
Machine Learning is one of the fastest-growing fields which has witnessed exponential growth in the technical world. But in this fast-growing field, the question is how to get started? Briefly this paper introduces various languages popular for machine learning and next it introduces a few math concepts that helps us understand what exactly is happ...
This paper presents a practical, and theoretically well-founded, approach to improve the speed of kernel manifold learning algorithms relying on spectral decomposition. Utilizing recent insights in kernel smoothing and learning with integral operators, we propose Reduced Set KPCA (RSKPCA), which also suggests an easy-to-implement method to remove o...
A plausible definition of “reasoning” could be “algebraically manipulating previously acquired knowledge in order to answer a new question”. This definition covers first-order logical inference or probabilistic inference. It also includes much simpler manipulations commonly used to build large learning systems. For instance, we can build an optical...