Maswali yanayounganishwa na mwongozo · Ngumu Kiwango

Mitandao ya Jimbo la Echo na Maswali ya Kompyuta ya Hifadhi

Hukagua mienendo ya hifadhi isiyobadilika, usomaji uliofunzwa, kumbukumbu inayofifia, radius ya spectral na hesabu nyuma ya utabiri wa hifadhi.

Njia za mwongozo zinazohusianaMitandao ya Jimbo la Echo na Kompyuta ya Hifadhi
Swali 1 ya 8

Katika Mtandao wa Jimbo la Echo, ni uzani gani ambao umefunzwa kweli?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Katika Mtandao wa Jimbo la Echo, ni uzani gani ambao umefunzwa kweli?
    • Uzito wa pato (kusoma) pekee
    • Uzito wote wa kawaida ndani ya hifadhi
    • Uzito wa pembejeo pekee
    • Hakuna uzito unaofunzwa
  2. Which condition expresses the echo state property for two runs with the same input history?
    • Their recurrent weights must all be trained by backpropagation
    • Their reservoir states eventually become independent of different initial states
    • Their output weights must have spectral radius exactly one
    • Their hidden states must equal the raw input at every step
  3. Kwa nini kufunza ESN ni haraka sana kuliko kufunza LSTM ya kawaida?
    • ESN hazitumii niuroni hata kidogo
    • ESN zinaendeshwa tu kwenye kompyuta za quantum
    • ESN huepuka uenezaji-kwa-muda kwa kutatua tu usomaji wa mstari
    • ESN hazihitaji data ya kuingiza
  4. How is spectral radius commonly used when tuning an echo-state reservoir?
    • It directly sets the number of readout classes
    • It guarantees fading memory for every recurrent matrix
    • It measures the number of trainable reservoir weights
    • It is a recurrent-feedback scale heuristic for balancing rich dynamics and stability, not a complete guarantee of the echo state property
  5. Mashine za Jimbo la Kimiminika, aina ya spiking-neuron ya kompyuta ya hifadhi, zilianzishwa na nani?
    • Wolfgang Maass
    • Geoffrey Hinton
    • Andrew Ng
    • Yoshua Bengio
  6. What does the fixed reservoir compute before the ESN readout produces an output?
    • A normalized probability over all possible weights
    • A high-dimensional dynamic state representation of recent inputs
    • A learned transition table for every future sequence
    • A separate trained policy for each output class
  7. What method is commonly used to fit an Echo State Network’s readout weights?
    • Backpropagation through all fixed recurrent weights
    • Dynamic routing by agreement
    • Linear least-squares regression, often with ridge regularization
    • A softmax over reservoir eigenvalues
  8. What does the spectral radius of a recurrent weight matrix mean?
    • The sum of all matrix entries
    • The number of nonzero output weights
    • The average magnitude of the input sequence
    • The largest absolute value among its eigenvalues