We present seven myths commonly believed to be true in machine learning research, circa Feb 2019. This is an archival copy of the blog post at https://crazyoscarchang.github.io/2019/02/16/seven-myths-in-machine-learning-research/ Myth 1: TensorFlow is a Tensor manipulation library Myth 2: Image datasets are representative of real images found in the wild Myth 3: Machine Learning researchers do not use the test set for validation Myth 4: Every datapoint is used in training a neural network Myth 5: We need (batch) normalization to train very deep residual networks Myth 6: Attention $>$ Convolution Myth 7: Saliency maps are robust ways to interpret neural networks
翻译:2019年2月2日,我们展示了7个一般认为在机器学习研究中是真实的神话。这是在https://crazyoscarccarchangh.github.io/2019/02/16/seven-myths-in-manch-in-learning-research/Myth1:Tensor Flow是一家Tensor操纵图书馆Myth 2:图像数据集代表野生神话中发现的真实图像:机器学习研究人员不使用验证神话的测试集:每一个数据点都用于神经网络培训Myth 5:我们需要(batch)对非常深的残余网络进行常规化培训Myth 6:注意 $> convolution myth 7:高度地图是解释神经网络的有力方法。