Questions tagged [recurrent-neural-network]

Question 1

I really want to play around with RNNs. Trying to build an AI assistant with RNNs to run on my machine as I'm always obsessed with RNNs model... To make the performance good, I think I need to do some ...

Question 2

The key equation for an RNN gives us a recurrence relation for the $\frac{\partial h_t}{\partial w_\textrm{h}}$ which are used later to compute the derivative of the loss through a simple chain rule. $...

Question 3

I do not understand this simple equality $$\frac{\partial h_t}{\partial w_\textrm{h}}= \frac{\partial f(x_{t},h_{t-1},w_\textrm{h})}{\partial w_\textrm{h}} +\frac{\partial f(x_{t},h_{t-1},w_\textrm{h})...

Question 4

I will use the answer here as an example: https://stats.stackexchange.com/a/370732/78063 It says "which means that you choose a number of time steps $N$, and unroll your network so that it ...

Question 5

I have an LSTM model to predict a variable by considering multiple variables. (Say the target variable is river discharge and the predictors are rainfall, temperature, evapotranspiration etc.) There ...

Question 6

In standard machine learning settings with cross-sectional data, it's common to assume that data points are independently and identically distributed (i.i.d.) from some fixed data-generating process (...

Question 7

I'm reading Murphy's PML and struggling with the derivation of this formula: $$p(\mathbf{y}_{1:T}|\mathbf{x}) = \sum_{\mathbf{h}_{1:T}} p(\mathbf{y}_{1:T}, \mathbf{h}_{1:T}|\mathbf{x}) = \sum_{\mathbf{...

Question 8

I have read somewhere (sorry, couldn't find the reference anymore), that $C_t$ (check figure below) represents the "long term" in LSMT. The reason was because "The information goes ...

Question 9

I am working on a time series prediction problem using an LSTM model. My dataset consists of 27 different items, each with unique IDs, and roughly the same number of samples per item. There are around ...

Question 10

Consider the following simple gated RNN: \begin{aligned} c_{t} &= \sigma\bigl(W_{c}\,x_{t} + W_{z}\,z_{t-1}\bigr) \\[6pt] z_{t} &= c_{t} \,\odot\, z_{t-1} \;\;+\;\; (1 - c_{t}) \,\odot\,\...

Question 11

I find it hard to understand the differences of the two. From what my understanding is that each hidden neuron in the FCRN influences all other neuron and itself while in the Hopfield it influences ...

Question 12

I am working on a project where I generate synthetic data which is the sum of 5 random sine functions sampled every 0.01s (and I add mean reverting brownian motion noise to the data). ...

Question 13

I have a bunch of time series with known real-world events (one event per t/s). An event is not necessarily visible as a change in the t/s, but is know to have occurred in the real world. I wonder if ...

Question 14

On October 9, 2024, the Nobel Foundation announced the Nobel Prize in Physics 2024 with the following statement of merit: for foundational discoveries and inventions that enable machine learning with ...

Question 15

I have a dataset of numerous years of buoy wave height measurements including features such as measured significant wave height, numerical model predictions, peak wave period, mean wave period, and ...

Stack Exchange Network

Questions tagged [recurrent-neural-network]

Is there a work on trying to pretrain RNNs model? [closed]

Is expanding the recurrence relation for RNNs useful in practice?

Simple questions about RNNs

Question on RNNs lookback window when unrolling

Is it possible to ignore the past values of the response variable in an LSTM model with multiple predictor variables?

Do i.i.d. assumptions extend to datasets of independently generated sequences in modern sequence models (e.g., RNNs)?

Vec2Seq Model Formula

Short and Long terms in LSTM

How to properly split train/val sets for time series LSTM prediction with multiple unique items?

Analytically solving backpropagation through time for a simple gated RNN

What are the differences between Fully recurrent neural networks Hopfield networks and Elman networks?

LSTM Limitations for Time Series Forecasting

What type of model/analysis to use to predict events in time series data

What are the works of Hopfield and Hinton that enable machine learning with neural networks, as noted in the physics Nobel award statement?

Should classical/traditional ML techniques such as polynomial regression/decision trees/random forests SIGNIFICANTLY outperform RNN in timeseries? [closed]

Hot Network Questions