dmccloskey / evonet Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
A class to simulate chromatograms.
Feature normalization: between net input and net output, performed across a feature set
addFeatureNormalization
method in ModuleBuilder
Barebones neural network framework
Convert classes and member to templates that allow for storage and arithmetic using defined precision
MNIST VAE example
Example Architecture
Objectives:
References:
Abstract base and inherited classes for various solvers
GUI to view a network
A method to define combinations of nodes/links/and weights as a "module" that can be copied, added, and deleted during model evolution
module_name
ModelReplicator
methods for copyModule
, addModule
, and deleteModule
Peak picking and integration using deep learning
Split management of weights and weight updates from Link class and into its own Weight class. Provide a link between the weight and the link it corresponds to using a "link_id." This will also provide a mechanisms for link sharing. In addition, a separate Solver class maybe needed to handle weight updates.
Write a modified file to disk
Class to automate the construction of networks. Would require a separate ModuleBuilder
class to define reusable sub units.
A class to calculate the modified EMG formulat
Abstract base and inherited classes for various loss functions
A method to management or optimize the number of devices and streams (GPUs) and threads (CPU) used based on user specifications and hardware configuration. The method should use a generic device abstraction to allow for multiple types of devices and new devices that may become available in the future.
Allow for multiple input integration strategies such as Sum, Product, and Max
implement interface for device specification when using the Eigen::Tensor library.
Similar to solver, weight_init, and activation
Model
to use shared_ptr implementation of NodeIntegrationNode
to use shared_ptr implementation of NodeIntegrationModelReplicator
to use shared_ptr implementation of NodeIntegrationRead a file from disk.
Some solutions to sequence problems can be found by disconnecting the output node. Need to implement a test to ensure that input can be propogated to the output.
set all node outputs to linear, set all biases to 0, set all weights to 1, set all inputs to 1, FP, and check that the output is > 1
Methods to allow for easy implementation of complex training schedules that involve adapting the population size, # of "mutations", etc., based on the network performance. In addition, it would be necessary to have methods to increase or decrease the difficulty of the task depending upon the network performance.
setRandomModifications
)n_top
, n_random
, and n_replicates_per_model
)A class to simulate a peak using an EMG model
multiple bugs were found in invalid calls to getRandom
(i.e., input vector of size 0) and insufficient handling of errors thrown by getRandom
. These occurred during rounds of training using PopulationTrainer.
Abstract base and inherited classes for various activation functions
R Hahnloser, R. Sarpeshkar, M A Mahowald, R. J. Douglas, H.S. Seung (2000). Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature. 405. pp. 947–951.
Clevert, Djork-Arné; Unterthiner, Thomas; Hochreiter, Sepp (2015). "Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)". arXiv:1511.07289
Time line plot to show the different models in the population during training
check to not add duplicate links
mechanism to decide on the NodeActivation
mechanism to decide on the NodeIntegration
implementations for drop connection and drop node during training. Implemented as a multiplication of the weight (drop connection) or the node output (drop node) by 0.
w=np.random.randn(layer_size[l],layer_size[l-1])*np.sqrt(2/layer_size[l-1])
Methods for logging model diagnostics during training to replace verbose outputs to the console
build only components of contrib needed
build only components of openMS needed
Toy models to use in order to test the properties of particular layers
Add in support for using Boost.Test unit testing module
Simulate a chromatogram with multiple peaks, varying baseline, and stochastic detector noise.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.