How can I find out the most impactful inputs to use as the predictors for the Recurrent Neural Network (RNN) modeling? I have a CSV file that has 25 columns and all of them are numeric. I want to predict one of the columns using the rest of the columns (24 columns). How can I find out how many of those 24 columns are impactful enough to be used as input using Mutual Information Analysis in python?
Usually Energy Disaggregation is done from a single input (grid consumption) to multiple outputs (appliances in a particular home). If you want to include multiple inputs, try building a multiple-input branch Neural Network and then stack your RNN layers.
You can also have a look this blog for a better understanding of Disaggregation.
If you want to get started with Energy Disaggregation and NILM using Deep Learning, you can have a look at this Open Source library: https://github.com/plexflo/plexflo. There is a Deep Learning model also included (LSTM) that can do basic Energy DIsaggregation.
Related
I want to build a neural network that will take the feature map from the last layer of a CNN (VGG or resnet for example), concatenate an additional vector (for example , 1X768 bert vector) , and re-train the last layer on classification problem.
So the architecture should be like in:
but I want to concat an additional vector to each feature vector (I have a sentence to describe each frame).
I have 5 possible labels , and 100 frames in the input frames.
Can someone help me as to how to implement this type of network?
I would recommend looking into the Keras functional API.
Unlike a sequential model (which is usually enough for many introductory problems), the functional API allows you to create any acyclic graph you want. This means that you can have two input branches, one for the CNN (image data) and the other for any NLP you need to do (relating to the descriptive sentence that you mentioned). Then, you can feed in the combined outputs of these two branches into the final layers of your network and produce your result.
Even if you've already created your model using models.Sequential(), it shouldn't be too hard to rewrite it to use the functional API.
For more information and implementation details, look at the official documentation here: https://keras.io/guides/functional_api/
My problem is that after creating and training a neural net with TensorFlow (version 2.1.0) I need to extrapolate all the basic parameters: net architecture, functions used and weight values found through training.
These parameters will then be read by a library that will generate the VHDL code to bring the neural network created on python on an FPGA.
So I wanted to ask if there are one or more methods to get all this information, not in binary format. Among all these values the most important one is the extrapolation of the value of the weights found at the end of the training.
I am looking to develop a simple Neural Network in PyTorch or TensorFlow to predict one numeric value based on several inputs.
For example, if one has data describing the interior comfort parameters for a building, the NN should predict the numeric value for the energy consumption.
Both PyTorch or TensorFlow documented examples and tutorials are generally focused on classification and time dependent series (which is not the case). Any idea on which NN available in those libraries is best for this kind of problems? I'm just looking for a hint about the type, not code.
Thanks!
The type of problem you are talking about is called a regression problem. In such types of problems, you would have a single output neuron with a linear activation (or no activation). You would use MSE or MAE to train your network.
If your problem is time series(where you are using previous values to predict current/next value) then you could try doing multi-variate time series forecasting using LSTMs.
If your problem is not time series, then you could just use a vanilla feed forward neural network. This article explains the concepts of data correlation really well and you might find it useful in deciding what type of neural networks to use based on the type of data and output you have.
Recurrent Neural Networks (RNN) With Attention Mechanism is generally used for Machine Translation and Natural Language Processing. In Python, implementation of RNN With Attention Mechanism is abundant in Machine Translation (For Eg. https://talbaumel.github.io/blog/attention/, however what I would like to do is to use RNN With Attention Mechanism on a temporal data file (not any textual/sentence based data).
I have a CSV file with of dimensions 21392 x 1972, which I have converted to a Dataframe using Pandas. The first column is of Datetime Format and last column consists of target classes like "Class1", "Class2", "Class3" etc. which I would like to identify. So in total, there are 21392 rows (instances of data in 10 minutes time-steps) and 1971 features. The last (1972th column) is the label column, with 14 different classes in total.
I have looked into available implementation documentation on Keras (https://medium.com/datalogue/attention-in-keras-1892773a4f22) as well as on Tensorflow (Visualizing attention activation in Tensorflow), but none of them seem to be doing what I want to accomplish. I understand that this is an unusual approach, but would want to try this and use the attention mechanism because many of my features are presumably redundant in the data.
import pandas as pd
mydataset = pd.read_csv('final_merged_data.csv')
It is predominant from existing literature that an Attention Mechanism works quite well when coupled into the RNN. I am unable to locate any such implementation of RNN with Attention Mechanism, which can also provide a visualisation as well. I am also unable to understand how I can convert my data into a sequence (or a list of lists) so that I can use it with One Hot Encoding afterwards for using RNN with Attention. I am new to using Python as well as Keras/Tensorflow, and am quite confused on the procedure to convert my data/typecast it to a form which will be able to mimic the sequence classification problem. My problem is basically of multi-class classification, like one would normally do using Machine Learning Classifiers to predict the labels, but using RNN with Attention. Any help in this regard would be highly appreciated. Cheers!
Kindly refer to this paper for using Sequence to Sequence Model with attention for time series classification.
https://www.computer.org/csdl/proceedings/icdmw/2016/5910/00/07836709.pdf
I have a set of 5 numbers as input and it produces output of 4 numbers. Need to find a model which can learn from the existing input/output and able to predict the numbers.
Go for recurrent neural networks or LSTM (Long-Short term memories). In simple terms, a feed-forward neural network simply produces output for given input based on the way it has figured out the relation between Input and Output while training, but it has no idea what the previous state (output) was, the basic idea is to recursively feed the output back to the input, i.e we make use of previous state of output along with current input as input to the neural network in a feedback loop fashion, so the output of neural network not only depends on the input but also on previous output.
LSTMs are being widely used for poetry generation, code-generation etc, your problem falls under the same domain.
Refer this link for more details: LSTM