Hopfield Network Algorithm with Solved Example
Вставка
- Опубліковано 19 вер 2024
- #softcomputing #neuralnetwork #datamining
Solved Example on Discrete Hopfield Network
Introduction:1.1 Biological neurons, McCulloch and Pitts models of neuron, Types
of activation function, Network architectures, Knowledge representation, Hebb net
1.2 Learning processes: Supervised learning, Unsupervised learning and
Reinforcement learning
1.3 Learning Rules : Hebbian Learning Rule, Perceptron Learning Rule, Delta
Learning Rule, Widrow-Hoff Learning Rule, Correlation Learning Rule, WinnerTake-All Learning Rule
1.4 Applications and scope of Neural Networks
10
2
Supervised Learning Networks :
2.1 Perception Networks - continuous & discrete, Perceptron convergence theorem,
Adaline, Madaline, Method of steepest descent, - least mean square algorithm,
Linear & non-linear separable classes & Pattern classes,
2.2 Back Propagation Network,
2.3 Radial Basis Function Network.
12
3
Unsupervised learning network:
3.1 Fixed weights competitive nets,
3.2 Kohonen Self-organizing Feature Maps, Learning Vector Quantization,
3.3 Adaptive Resonance Theory - 1
06
4
Associative memory networks:
4.1 Introduction, Training algorithms for Pattern Association,
4.2 Auto-associative Memory Network, Hetero-associative Memory Network,
Bidirectional Associative Memory,
4.3 Discrete Hopfield Networks.
08
5
Fuzzy Logic:
5.1 Fuzzy Sets, Fuzzy Relations and Tolerance and Equivalence
5.2 Fuzzification and Defuzzification
5.3 Fuzzy Controllers
Thank you for such an easy and understandable explanation for a complex topic. helped me alot!
I really appreciated man, even though I cannot understand Hindi at all, I got your explanation thoroughly because of your simple but precise example that covered all material. You are better than my prof who studied whole his life in France. Actually, I love teaching but I need to learn well, not like my prof.
God bless India ;-)
Bhaiya ur ruling the soft computing topics in u tube.. Thank u dude.
Eyvallah kardeşim. as far as you explained better than our teacher. thank u
Are you Turkish marhaba
Best video.
Amazing video brother! Keep up the good work!
thank you bhai kl paper hai artificial neural network ka aap ne hopfield bohot ache se samjha diya
it helps me helps a lot ... Thanks Brother
Bro you are a Gem💯
Why do we convert to binary for testing. Can't we keep it as it is?
thank you very much,, This video really helped me..
Super Explanation brother -----------------keep going on
Awesome video bro!
Good job man....helped alot
Really Nice explaination......
Man, your bam video was very clear, but i dont know what you are saying in this video
very good explanation....
thank you so much
Thank you very much
Thank u so much.. Remarkable:)
3:35 in calculation of weight matrix I think you meant S^T(P).S(P) instead of S^T(P).t(P) since there is no output matrix . Is that right?
yes it is right, it is outer product rule
Thank you
Very helpful sir👏😊
Watch in ^ .75
super super super
Bhai seedha he kr deta Y=X + X*W where X, Y, W are the corresponding matrices for input, output and weight.
Yes bro you are right.....Time waste kr diya.
Thanku sir
Tu GOD he bro
I don't get the language, but the explanation was great
Is it a convention that after chosing y1 unit for updation, we have to chose y4 for updation & then y3 & y2...
Can we update y2 unit just after y1 unit???
Yes you can !!
What is this language? Or languages? Hinglish?
At step 4 :- when u calculating y4 0+1= 1 will come u kept as -2 bro .I think its wrong , u Just rectify that mistake
Yes it would be
[1 0 1 0] 1 = 1+1=2.
0
1
-1
This not hopfield, this discrete Hopfield. Brother btw nice video
Y1 ke bad agr randomly na lkr serially koi input choose kare to jese y1,y2 tb v same aayega?
Tomorrow exam and I'm here at 12 am 😁 🙏
What happens if it doesn't converge at all
Why did u choose input vector directly
Can you please provide notes
anyone to translate for me as how to get the x and y vectors...
Eyy weBafo lo mfo akaykhulumi lento esiyfunayo
@4.13 how did you calculated binary representation for (1,1,1,-1) to (1,1,1,0)
Bipolar to binary. Assume in bipolar -1 = 0 and +1=1. Actually the matrix [1,1,1,-1] is [+1,+1,+1,-1]
@@saranshkhurana7784 thanks man
Binary kyo liya.
Do you have it in English?
what language is this?
hindi
mexican
Klingon? @@rohanwarghade7111
Hindi
Which country are you from?
thanks bro lol
Huu, sound at beginning of video...kis kis me notice kiya😄🙈
implement the code in matlab please
Bhai yrr apne in notes ki pdf dede bhai plz😢😭😭😭😭😭😭😭😭😭😭😭😭😭😭😭😭😭😭😭😭😭😭....
nxt time onwards plss explain in English bro.
Pehle explain toh karte kya hota he hopfeild
Bro, what the fuck
Jai jai bajrangbali
cant get shit about what you said. Not helpful
bhai thodi padhai likhai kar le
English bro ?!