tf.erf(x, name=None) Computes the Gauss error function of x element-wise. Args:

tf.complex_abs(x, name=None) Computes the complex absolute value of a tensor. Given a tensor x

tf.where(input, name=None) Returns locations of true values in a boolean tensor. This operation

tf.argmin(input, dimension, name=None) Returns the index with the smallest value across dimensions of a tensor.

tf.add_n(inputs, name=None) Adds all input tensors element-wise. Args:

tf.cholesky(input, name=None) Computes the Cholesky decomposition of one or more square matrices. The

tf.fft2d(input, name=None) Compute the 2-dimensional discrete Fourier Transform over the inner-most 2

tf.pow(x, y, name=None) Computes the power of one value to another. Given a tensor x

tf.truediv(x, y, name=None) Divides x / y elementwise, always producing floating point results. The

tf.reduce_prod(input_tensor, reduction_indices=None, keep_dims=False, name=None) Computes the product of elements across dimensions