دانلود مقاله انگلیسی رایگان:یادگیری عمیق زیست شناختی قابل قبول: اما تا چه حد می توانیم با شبکه های کم عمق برویم؟ - 2019
دانلود بهترین مقالات isi همراه با ترجمه فارسی
دانلود مقاله انگلیسی یادگیری عمیق رایگان
  • Biologically plausible deep learning—But how far can we go with shallow networks? Biologically plausible deep learning—But how far can we go with shallow networks?
    Biologically plausible deep learning—But how far can we go with shallow networks?

    سال انتشار:

    2019


    عنوان انگلیسی مقاله:

    Biologically plausible deep learning—But how far can we go with shallow networks?


    ترجمه فارسی عنوان مقاله:

    یادگیری عمیق زیست شناختی قابل قبول: اما تا چه حد می توانیم با شبکه های کم عمق برویم؟


    منبع:

    Sciencedirect - Elsevier - Neural Networks, 118 (2019) 90-101: doi:10:1016/j:neunet:2019:06:001


    نویسنده:

    Bernd Illing ∗, Wulfram Gerstner, Johanni Brea


    چکیده انگلیسی:

    Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning, typically defining success as reaching around 98% test accuracy on the MNIST data set. Here, we investigate how far we can go on digit (MNIST) and object (CIFAR10) classification with biologically plausible, local learning rules in a network with one hidden layer and a single readout layer. The hidden layer weights are either fixed (random or random Gabor filters) or trained with unsupervised methods (Principal/Independent Component Analysis or Sparse Coding) that can be implemented by local learning rules. The readout layer is trained with a supervised, local learning rule. We first implement these models with rate neurons. This comparison reveals, first, that unsupervised learning does not lead to better performance than fixed random projections or Gabor filters for large hidden layers. Second, networks with localized receptive fields perform significantly better than networks with all-to-all connectivity and can reach backpropagation performance on MNIST. We then implement two of the networks – fixed, localized, random & random Gabor filters in the hidden layer – with spiking leaky integrate-and-fire neurons and spike timing dependent plasticity to train the readout layer. These spiking models achieve >98.2% test accuracy on MNIST, which is close to the performance of rate networks with one hidden layer trained with backpropagation. The performance of our shallow network models is comparable to most current biologically plausible models of deep learning. Furthermore, our results with a shallow spiking network provide an important reference and suggest the use of data sets other than MNIST for testing the performance of future models of biologically plausible deep learning.
    Keywords: Deep learning | Local learning rules | Random projections | Unsupervised feature learning | Spiking networks | MNIST


    سطح: متوسط
    تعداد صفحات فایل pdf انگلیسی: 12
    حجم فایل: 952 کیلوبایت

    قیمت: رایگان


    توضیحات اضافی:




اگر این مقاله را پسندیدید آن را در شبکه های اجتماعی به اشتراک بگذارید (برای به اشتراک گذاری بر روی ایکن های زیر کلیک کنید)

تعداد نظرات : 0

الزامی
الزامی
الزامی
rss مقالات ترجمه شده rss مقالات انگلیسی rss کتاب های انگلیسی rss مقالات آموزشی