Lines Matching full:neural

7 - Deep neural networks built on a tape-based autograd system
17   - [Dynamic Neural Networks: Tape-Based Autograd](#dynamic-neural-networks-tape-based-autograd)
59 | [**torch.nn**](https://pytorch.org/docs/stable/nn.html) | A neural networks library deeply integr…
83 ### Dynamic Neural Networks: Tape-Based Autograd
85 PyTorch has a unique way of building neural networks: using and replaying a tape recorder.
88 One has to build a neural network and reuse the same structure again and again.
108 You can write your new neural network layers in Python itself, using your favorite libraries
124 At the core, its CPU and GPU Tensor and neural network backends
127 Hence, PyTorch is quite fast — whether you run small or large neural networks.
136 Writing new neural network modules, or interfacing with PyTorch's Tensor API was designed to be str…
139 You can write new neural network layers in Python using the torch API
464 * [Deep Neural Networks with PyTorch from Coursera](https://www.coursera.org/learn/deep-neural-netw…