Tensor Classification Models Aside from Convolution Neural Networks, are there any other methods that allow for classification of Tensors? My observations consist of  multi-dimensional tensors with height of 1, where each channel corresponds to a particular time-series and am wondering how I can effectively classify the tensors, taking into account the relationship between the time-series. 
 A: You can flatten the tensor and run the usual machine learning methods on the vector: random forest, kNN, SVM, logistic regression, multilayer perceptron neural networks, etc.
This has been done for $2$-tensors like the MNIST digits, and the strategy could be applied to higher-order tensors, too.
A: Recurrent neural networks might be an option. These have the capability of keeping information in a time series and are used for signals in time domain, for applications such as speech recognition etc... LSTM is a variant of these which is also widely used. 
A: Basically, your data consists of multivariate timeseries.
Since you have a time-varying dimension, you are looking at a few models that can do that.

*

*1D Convolutional Neural Networks: convolutions are applied in the time dimension. Then usual pooling operations are used to reduce the dimensionality to a single output.

*Recurrent Neural Networks: RNNs are applied and you either keep the last (in time) output or pool across the whole time dimension. It's very usual to use Bi-directional RNNs here as well.

*Transformers: Attention layers are used to obtain new time-distributed representations. You can then pool as usual, or use attention itself to obtain a single vector-representation for the whole sequence.

If the timeseries are aligned (like, for example, all multivariate timeseries represent a process after a trigger/stimulus onset), then you can also use Functional Data Analysis (FDA) tools. These are usually based on basis expansion of the data itself.
