विधियों की तुलना करें

	वैरिएशनल ऑटोएन्कोडर के साथ ट्रांसफर लर्निंग	कनवोल्यूशनल न्यूरल नेटवर्क के साथ ट्रांसफर लर्निंग
क्षेत्र	गहन अधिगम	गहन अधिगम
परिवार	Machine learning	Machine learning
उद्भव वर्ष	2014 (VAE); 2010 (transfer learning survey)	2010–2014
प्रवर्तक	Kingma, D. P. & Welling, M. (VAE); transfer learning framework from Pan & Yang	Pan, S. J. & Yang, Q. (transfer learning framework); popularized for CNNs by Yosinski et al. and Razavian et al.
प्रकार	Generative model with transferred encoder/decoder	Transfer learning applied to convolutional neural networks
मौलिक स्रोत	Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR 2014).	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
उपनाम	TL-VAE, pretrained VAE, VAE transfer learning, fine-tuned variational autoencoder	TL-CNN, pretrained CNN, CNN fine-tuning, feature-extracting CNN
संबंधित	6	4
सारांश	Transfer Learning with a Variational Autoencoder (TL-VAE) reuses an encoder and/or decoder pre-trained on a large source dataset and adapts it to a smaller target domain. By inheriting a rich probabilistic latent space rather than starting from random weights, TL-VAE dramatically reduces the amount of target-domain data needed for high-quality generation or representation learning.	Transfer Learning with CNN reuses a convolutional neural network that has already been trained on a large dataset — most commonly ImageNet — and adapts its learned feature detectors to a new, often smaller target dataset. This lets researchers achieve strong image-recognition performance without the massive compute and data resources required to train a CNN from scratch.