**Single-Path NAS** is a convolutional neural network architecture discovered through the Single-Path [neural architecture search](https://paperswithcode.com/method/neural-architecture-search) approach. The NAS utilises a single-path search space. Specifically, compared to previous differentiable  NAS methods, Single-Path NAS uses one single-path over-parameterized  ConvNet to encode all architectural decisions with shared convolutional kernel parameters. The approach is built upon the  observation that different candidate convolutional operations in NAS  can be viewed as subsets of a single superkernel. Without having to  choose among different paths/operations as in multi-path methods, we instead  solve the NAS problem as finding which subset of kernel weights to use in each ConvNet layer. By sharing the convolutional kernel weights,  we encode all candidate NAS operations into a single superkernel.

The architecture itself uses the [inverted residual block](https://paperswithcode.com/method/inverted-residual-block) from [MobileNetV2](https://paperswithcode.com/method/mobilenetv2) as its basic building block.

An aspect of Bi-RNNs that could be undesirable is the architecture's symmetry in both time directions.

 Bi-RNNs are often used in natural language processing, where the order of the words is almost exclusively determined by grammatical rules and not by temporal sequentiality.  However, in some cases, the data has a preferred direction in time: the forward direction. 

Another potential drawback of Bi-RNNs is that their output is simply the concatenation of two naive readings of the input in both directions. In consequence, Bi-RNNs never actually read an input by knowing what happens in the future. Conversely, the idea behind U-RNN, is to first do a backward pass, and then use during the forward pass information about the future.

We accumulate information while knowing which part of the information will be useful in the future as it should be relevant to do so if the forward direction is the preferred direction of the data.

The backward and forward hidden states $(h^b_t)$ and  $(h^f_t)$ are obtained according to these equations:

\begin{equation}
\begin{aligned}
&h_{t-1}^{b}=R N N\left(h_{t}^{b}, e_{t}, W_{b}\right) \\
&h_{t+1}^{f}=R N N\left(h_{t}^{f},\left[e_{t}, h_{t}^{b}\right], W_{f}\right)
\end{aligned}
\end{equation}

where $W_b$ and $W_f$ are learnable weights that are shared among pedestrians, and $[\cdot, \cdot]$ denotes concatenation. The last hidden state $h^f_{T_{obs}}$ is then used as the encoding of the sequence.

U-RNNs

Source	Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com