This document summarizes a Chainer meetup where Yuta Kashino presented on PyTorch. Key points discussed include: - Yuta Kashino is the CEO of BakFoo, Inc. and discussed his background in astrophysics, Zope, and Python. - PyTorch was introduced as an alternative to Chainer and TensorFlow that is Pythonic and defines models dynamically through code. - PyTorch uses autograd to track gradients like Ch
![私は如何にして心配するのを止めてPyTorchを愛するようになったか](https://cdn-ak-scissors.b.st-hatena.com/image/square/d8e541af2d98d2d81061da6991e6b20900847c36/height=288;version=1;width=512/https%3A%2F%2Fcdn.slidesharecdn.com%2Fss_thumbnails%2Fchainermu2017-09-30-170930041816-thumbnail.jpg%3Fwidth%3D640%26height%3D640%26fit%3Dbounds)