{"id":31003634,"url":"https://github.com/accel-brain/accel-brain-code","last_synced_at":"2025-10-30T20:58:05.165Z","repository":{"id":49317496,"uuid":"103709988","full_name":"accel-brain/accel-brain-code","owner":"accel-brain","description":"The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and research and development(R\u0026D) that I have written in my website. The main research topics are Auto-Encoders in relation to the representation learning, the statistical machine learning for energy-based models, adversarial generation networks(GANs), Deep Reinforcement Learning such as Deep Q-Networks, semi-supervised learning, and neural network language model for natural language processing.","archived":false,"fork":false,"pushed_at":"2023-12-26T03:01:38.000Z","size":103040,"stargazers_count":320,"open_issues_count":1,"forks_count":92,"subscribers_count":18,"default_branch":"master","last_synced_at":"2025-10-26T09:58:32.985Z","etag":null,"topics":["auto-encoder","automatic-summarization","combinatorial-optimization","deep-learning","deep-q-network","deep-reinforcement-learning","energy-based-model","generative-adversarial-network","lstm","multi-agent-reinforcement-learning","q-learning","quantum-annealing","quantum-monte-carlo","reinforcement-learning","restricted-boltzmann-machine","self-supervised-learning","semi-supervised-learning","simulated-annealing","transfer-learning"],"latest_commit_sha":null,"homepage":"https://accel-brain.co.jp","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/accel-brain.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2017-09-15T23:37:39.000Z","updated_at":"2025-10-18T17:19:26.000Z","dependencies_parsed_at":"2024-01-16T15:51:59.973Z","dependency_job_id":null,"html_url":"https://github.com/accel-brain/accel-brain-code","commit_stats":{"total_commits":1784,"total_committers":9,"mean_commits":"198.22222222222223","dds":0.4136771300448431,"last_synced_commit":"bc67ffc411d83b948d04869322b4068022d040bf"},"previous_names":["chimera0/accel-brain-code"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/accel-brain/accel-brain-code","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/accel-brain%2Faccel-brain-code","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/accel-brain%2Faccel-brain-code/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/accel-brain%2Faccel-brain-code/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/accel-brain%2Faccel-brain-code/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/accel-brain","download_url":"https://codeload.github.com/accel-brain/accel-brain-code/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/accel-brain%2Faccel-brain-code/sbom","scorecard":{"id":162302,"data":{"date":"2025-08-11","repo":{"name":"github.com/accel-brain/accel-brain-code","commit":"cffeaa28e541a70162b63a5f849e61661db7492e"},"scorecard":{"version":"v5.2.1-40-gf6ed084d","commit":"f6ed084d17c9236477efd66e5b258b9d4cc7b389"},"score":3.5,"checks":[{"name":"Packaging","score":-1,"reason":"packaging workflow not detected","details":["Warn: no GitHub/GitLab publishing workflow detected."],"documentation":{"short":"Determines if the project is published as a package that others can easily download, install, easily update, and uninstall.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#packaging"}},{"name":"Maintained","score":0,"reason":"0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project is \"actively maintained\".","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#maintained"}},{"name":"Dangerous-Workflow","score":-1,"reason":"no workflows found","details":null,"documentation":{"short":"Determines if the project's GitHub Action workflows avoid dangerous patterns.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#dangerous-workflow"}},{"name":"Code-Review","score":0,"reason":"Found 0/30 approved changesets -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project requires human code review before pull requests (aka merge requests) are merged.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#code-review"}},{"name":"CII-Best-Practices","score":0,"reason":"no effort to earn an OpenSSF best practices badge detected","details":null,"documentation":{"short":"Determines if the project has an OpenSSF (formerly CII) Best Practices Badge.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#cii-best-practices"}},{"name":"Token-Permissions","score":-1,"reason":"No tokens found","details":null,"documentation":{"short":"Determines if the project's workflows follow the principle of least privilege.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#token-permissions"}},{"name":"Security-Policy","score":0,"reason":"security policy file not detected","details":["Warn: no security policy file detected","Warn: no security file to analyze","Warn: no security file to analyze","Warn: no security file to analyze"],"documentation":{"short":"Determines if the project has published a security policy.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#security-policy"}},{"name":"SAST","score":0,"reason":"no SAST tool detected","details":["Warn: no pull requests merged into dev branch"],"documentation":{"short":"Determines if the project uses static code analysis.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#sast"}},{"name":"Binary-Artifacts","score":10,"reason":"no binaries found in the repo","details":null,"documentation":{"short":"Determines if the project has generated executable (binary) artifacts in the source repository.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#binary-artifacts"}},{"name":"License","score":10,"reason":"license file detected","details":["Info: project has a license file: LICENSE:0","Info: FSF or OSI recognized license: GNU General Public License v2.0: LICENSE:0"],"documentation":{"short":"Determines if the project has defined a license.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#license"}},{"name":"Fuzzing","score":0,"reason":"project is not fuzzed","details":["Warn: no fuzzer integrations found"],"documentation":{"short":"Determines if the project uses fuzzing.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#fuzzing"}},{"name":"Vulnerabilities","score":10,"reason":"0 existing vulnerabilities detected","details":null,"documentation":{"short":"Determines if the project has open, known unfixed vulnerabilities.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#vulnerabilities"}},{"name":"Signed-Releases","score":-1,"reason":"no releases found","details":null,"documentation":{"short":"Determines if the project cryptographically signs release artifacts.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#signed-releases"}},{"name":"Branch-Protection","score":-1,"reason":"internal error: error during branchesHandler.setup: internal error: githubv4.Query: Resource not accessible by integration","details":null,"documentation":{"short":"Determines if the default and release branches are protected with GitHub's branch protection settings.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#branch-protection"}},{"name":"Pinned-Dependencies","score":-1,"reason":"no dependencies found","details":null,"documentation":{"short":"Determines if the project has declared and pinned the dependencies of its build process.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#pinned-dependencies"}}]},"last_synced_at":"2025-08-16T13:50:18.043Z","repository_id":49317496,"created_at":"2025-08-16T13:50:18.043Z","updated_at":"2025-08-16T13:50:18.043Z"},"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281602436,"owners_count":26529317,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-29T02:00:06.901Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["auto-encoder","automatic-summarization","combinatorial-optimization","deep-learning","deep-q-network","deep-reinforcement-learning","energy-based-model","generative-adversarial-network","lstm","multi-agent-reinforcement-learning","q-learning","quantum-annealing","quantum-monte-carlo","reinforcement-learning","restricted-boltzmann-machine","self-supervised-learning","semi-supervised-learning","simulated-annealing","transfer-learning"],"created_at":"2025-09-13T01:24:37.457Z","updated_at":"2025-10-30T20:58:05.148Z","avatar_url":"https://github.com/accel-brain.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Accel Brain Code: From Proof of Concept to Prototype.\n\nThe purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and research and development(R\u0026D) that I have written in my website: [Accel Brain](https://accel-brain.com) (Japanese) and [Accel Brain Co., Ltd.](https://accel-brain.co.jp/) (Japanese). The main research topics are Auto-Encoders in relation to the representation learning, the statistical machine learning for energy-based models, adversarial generation networks(GANs), Deep Reinforcement Learning such as Deep Q-Networks, semi-supervised learning, and neural network language model for natural language processing.\n\n## Problem Setting: Deep Learning after the era of \"Democratization of Artificial Intelligence(AI)\".\n\nHow the Research and Development(R\u0026D) on the subject of machine learning including deep learning, after the era of \"Democratization of Artificial Intelligence(AI)\", can become possible? Simply implementing the models and algorithms provided by standard machine learning libraries and applications like AutoML would reinvent the wheel. If you just copy and paste the demo code from the library and use it, your R\u0026D would fall into dogmatically authoritarian development, or so-called the Hype driven development.\n\nIf you fall in love with the concept of \"Democratization of AI,\" you may forget the reality that the R\u0026D is under the influence of not only democracy but also capitalism. The R\u0026D provides economic value when its R\u0026D artifacts are distinguished from the models and algorithms realized by standard machine learning libraries and applications such as AutoML. In general terms, R\u0026D must provide a differentiator to maximize the scarcity of its implementation artifacts.\n\nOn the other hand, it must be remembered that any R\u0026D builds on the history of the social structure and the semantics of the concepts envisioned by previous studies. Many models and algorithms are variants derived not only from research but also from the relationship with business domains. It is impossible to assume differentiating factors without taking commonality and identity between society and its history.\n\n### Problem Solution: PoC of PoC.\n\nThe blind spot of \"democratization of AI\" occurs when a new concept is created throughout the society, including business. It takes time before a new concept can be broken down into an interface specification from a perspective such as object-oriented analysis, and code that conforms to the interface specification can be implemented. There will always be some difference between the new AI created in this way and the AI already \"democratized\". \n\nIn a more realistic perspective, casual users who are just waiting for the AI to be \"democratized\" will always fall behind. On the contrary, those who can create new concepts and new AIs with PoC will always continue to have a leading advantage in the market where AI is the main topic. Hiding behind the \"democratic\" movement of \"AI democratization\" is the dry reality of \"capitalist\" competition.\n\n#### Lifehack of Lifehack.\n\nThe basic theme in my PoC is a Lifehack, which is any technique that reduces the burden of our life and make it easier to control, or more convenient. Considering that many lifehack solutions are technological and obviously product design and development technology are kind of *life* which can be *hacked*, lifehack itself also can be purpose of lifehack. Because of this *Autologie*, a seemingly endless round of my PoC and technological prototypes is rotary driven by *Selbstreferenz* to repeat *lifehack of lifehack* cyclically.\n\nIn this problem setting and *recursive* solutions, this repository is functionally differentiated by compositions such as information collection, searching optimal solution, and focus booster. Each function can be considered an integral component of lifehack solutions. These tools make it possible to efficiency the process of contemplation and accelerate our brain, enabling provisions for the developments of other tools in this repository. All code, implemented as in an algorithm of machine learning or data science, reflects the concept of proof of concept(PoC). \n\n### Problem Solution: [Accel-Brain-Base](https://github.com/accel-brain/accel-brain-code/tree/master/Accel-Brain-Base).\n\nAs part of prototyping, this repository publishes a special machine learning library, [Accel-Brain-Base](https://github.com/accel-brain/accel-brain-code/tree/master/Accel-Brain-Base).\n\n`accel-brain-base` is a basic library of the Deep Learning for rapid development at low cost. This library makes it possible to design and implement deep learning, which must be configured as a complex system or a System of Systems, by combining a plurality of functionally differentiated modules such as a Restricted Boltzmann Machine(RBM), Deep Boltzmann Machines(DBMs), a Stacked-Auto-Encoder, an Encoder/Decoder based on Long Short-Term Memory(LSTM), and a Convolutional Auto-Encoder(CAE).\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"https://storage.googleapis.com/accel-brain-code/Deep-Learning-by-means-of-Design-Pattern/img/horse099.jpg\" /\u003e\n\u003cp\u003eImage in \u003ca href=\"https://avaminzhang.wordpress.com/2012/12/07/%E3%80%90dataset%E3%80%91weizmann-horses/\" target=\"_blank\"\u003ethe Weizmann horse dataset\u003c/a\u003e.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"https://storage.googleapis.com/accel-brain-code/Deep-Learning-by-means-of-Design-Pattern/img/reconstructed_by_CAE.gif\" /\u003e\n\u003cp\u003eReconstructed image by \u003cstrong\u003eConvolutional Auto-Encoder\u003c/strong\u003e.\u003c/p\u003e\n\u003c/div\u003e\n\nFrom the view points of functionally equivalents and structural expansions, this library also prototypes many variants such as energy-based models and Generative models. Typical examples are Generative Adversarial Networks(GANs) and Adversarial Auto-Encoders(AAEs). In addition, it provides deep reinforcement learning that applies the neural network described above as a function approximator.\n\nConsidering many variable parts, structural unions, and *functional equivalents* in the deep learning paradigm, which are variants derived not only from research but also from the relationship with business domains, from perspective of *commonality/variability analysis* in order to practice object-oriented design, this library provides abstract classes that define the skeleton of the deep Learning algorithm in an operation, deferring some steps in concrete variant algorithms such as the **Deep Boltzmann Machines**, **Stacked Auto-Encoder**, **Encoder/Decoder based on LSTM**, and **Convolutional Auto-Encoder** to client subclasses. The abstract classes and the interfaces in this library let subclasses redefine certain steps of the deep Learning algorithm without changing the algorithm's structure.\n\nThese abstract classes can also provide new original models and algorithms such as **Generative Adversarial Networks(GANs)**, **Deep Reinforcement Learning**, or **Neural network language model** by implementing the variable parts of the fluid elements of objects.\n\n#### Documentation\n\nFull documentation is available on [https://code.accel-brain.com/Accel-Brain-Base/README.html](https://code.accel-brain.com/Accel-Brain-Base/README.html). This document contains information on functionally reusability, functional scalability and functional extensibility.\n\n### Problem Solution: [Automatic Summarization Library: pysummarization](https://github.com/chimera0/accel-brain-code/tree/master/Automatic-Summarization)\n\n`pysummarization` is Python3 library for the automatic summarization, document abstraction, and text filtering.\n\nThe function of this library is automatic summarization using a kind of natural language processing. This library enable you to create a summary with the major points of the original document or web-scraped text that filtered by text clustering.\n\n#### Documentation\n\nFull documentation is available on [https://code.accel-brain.com/Automatic-Summarization/](https://code.accel-brain.com/Automatic-Summarization/) . This document contains information on functionally reusability, functional scalability and functional extensibility.\n\n### Problem Solution: [Reinforcement Learning Library: pyqlearning](https://github.com/chimera0/accel-brain-code/tree/master/Reinforcement-Learning)\n\n`pyqlearning` is Python library to implement Reinforcement Learning and Deep Reinforcement Learning, especially for Q-Learning, Deep Q-Network, and Multi-agent Deep Q-Network which can be optimized by Annealing models such as Simulated Annealing, Adaptive Simulated Annealing, and Quantum Monte Carlo Method.\n\nAccording to the Reinforcement Learning problem settings, Q-Learning is a kind of **Temporal Difference learning(TD Learning)** that can be considered as hybrid of **Monte Carlo** method and **Dynamic Programming** method. As Monte Carlo method, TD Learning algorithm can learn by experience without model of environment. And this learning algorithm is functional extension of bootstrap method as Dynamic Programming Method.\n\n#### The commonality/variability of Q-Learning.\n\nIn this library, Q-Learning can be distinguished into **Epsilon Greedy Q-Leanring** and **Boltzmann Q-Learning**. These algorithm is functionally equivalent but their structures should be conceptually distinguished.\n\nConsidering many variable parts and functional extensions in the Q-learning paradigm from perspective of *commonality/variability* analysis in order to practice object-oriented design, this library provides abstract class that defines the skeleton of a Q-Learning algorithm in an operation, deferring some steps in concrete variant algorithms such as Epsilon Greedy Q-Leanring and Boltzmann Q-Learning to client subclasses. The abstract class in this library lets subclasses redefine certain steps of a Q-Learning algorithm without changing the algorithm's structure.\n\n#### Simple Maze Solving by Deep Q-Network\n\n[demo/search_maze_by_deep_q_network.ipynb](https://github.com/chimera0/accel-brain-code/blob/master/Reinforcement-Learning/demo/search_maze_by_deep_q_network.ipynb) is a Jupyter notebook which demonstrates a maze solving algorithm based on Deep Q-Network, rigidly coupled with Deep Convolutional Neural Networks(Deep CNNs). The function of the Deep Learning is **generalisation** and CNNs is-a **function approximator**. In this notebook, several functional equivalents such as CNN, Long Short-Term Memory(LSTM) networks, and the model which loosely coupled CNN and LSTM can be compared from a functional point of view.\n\n\u003cdiv align=\"center\"\u003e\n    \u003cp\u003e\u003ca href=\"https://github.com/chimera0/accel-brain-code/blob/master/Reinforcement-Learning/demo/search_maze_by_deep_q_network.ipynb\" target=\"_blank\"\u003e\u003cimg src=\"https://storage.googleapis.com/accel-brain-code/Reinforcement-Learning/img/DQN_single_agent_goal_compressed.gif\" /\u003e\u003c/a\u003e\u003c/p\u003e\n    \u003cp\u003eDeep Reinforcement Learning to solve the Maze.\u003c/p\u003e\n\u003c/div\u003e\n\n* Black squares represent a wall.\n* Light gray squares represent passages.\n* A dark gray square represents a start point.\n* A white squeare represents a goal point.\n\n##### The pursuit-evasion game\n\nExpanding the search problem of the maze makes it possible to describe the pursuit-evasion game that is a family of problems in mathematics and computer science in which one group attempts to track down members of another group in an environment.\n\nThis problem can be re-described as the multi-agent control problem, which involves decomposing the global system state into an image like representation with information encoded in separate channels. This reformulation allows us to use convolutional neural networks to efficiently extract important features from the image-like state.\n\n[demo/search_maze_by_deep_q_network.ipynb](https://github.com/chimera0/accel-brain-code/blob/master/Reinforcement-Learning/demo/search_maze_by_deep_q_network.ipynb) also prototypes Multi Agent Deep Q-Network to solve the pursuit-evasion game based on the image-like state representation of the multi-agent.\n\n\u003cdiv align=\"center\"\u003e\n    \u003ctable style=\"border: none;\"\u003e\n        \u003ctr\u003e\n            \u003ctd width=\"45%\" align=\"center\"\u003e\n            \u003cp\u003e\u003ca href=\"https://github.com/chimera0/accel-brain-code/blob/master/Reinforcement-Learning/demo/search_maze_by_deep_q_network.ipynb\" target=\"_blank\"\u003e\u003cimg src=\"https://storage.googleapis.com/accel-brain-code/Reinforcement-Learning/img/DQN_multi_agent_demo_crash_enemy_2-compressed.gif\" /\u003e\u003c/a\u003e\u003c/p\u003e\n            \u003cp\u003eMulti-agent Deep Reinforcement Learning to solve the pursuit-evasion game. The player is caught by enemies.\u003c/p\u003e\n            \u003c/td\u003e\n            \u003ctd width=\"45%\" align=\"center\"\u003e\n            \u003cp\u003e\u003ca href=\"https://github.com/chimera0/accel-brain-code/blob/master/Reinforcement-Learning/demo/search_maze_by_deep_q_network.ipynb\" target=\"_blank\"\u003e\u003cimg src=\"https://storage.googleapis.com/accel-brain-code/Reinforcement-Learning/img/DQN_multi_agent_demo_goal_enemy_2-compressed.gif\" /\u003e\u003c/a\u003e\u003c/p\u003e\n            \u003cp\u003e\n            \u003cp\u003eMulti-agent Deep Reinforcement Learning to solve the pursuit-evasion game. The player reaches the goal.\u003c/p\u003e\n            \u003c/td\u003e\n        \u003c/tr\u003e\n    \u003c/table\u003e\n\u003c/div\u003e\n\n* Black squares represent a wall.\n* Light gray squares represent passages.\n* A dark gray square represents a start point.\n* Moving dark gray squares represent enemies.\n* A white squeare represents a goal point.\n\n#### Combinatorial optimization problem and Simulated Annealing.\n\nThere are many hyperparameters that we have to set before the actual searching and learning process begins. Each parameter should be decided in relation to Reinforcement Learning theory and it cause side effects in training model. This issue can be considered as **Combinatorial optimization problem** which is an optimization problem, where an optimal solution has to be identified from a finite set of solutions. In this problem setting, this library provides an Annealing Model such as **Simulated Annealing** to search optimal combination of hyperparameters. \n\nAs exemplified in [annealing_hand_written_digits.ipynb](https://github.com/chimera0/accel-brain-code/blob/master/Reinforcement-Learning/annealing_hand_written_digits.ipynb), there are many functional extensions and functional equivalents of Simulated Annealing. For instance, **Adaptive Simulated Annealing**, also known as the very fast simulated reannealing, is a very efficient version of simulated annealing. And **Quantum Monte Carlo**, which is generally known a stochastic method to solve the Schrödinger equation, is one of the earliest types of solution in order to simulate the **Quantum Annealing** in classical computer.\n\n#### Documentation\n\nFull documentation is available on [https://code.accel-brain.com/Reinforcement-Learning/](https://code.accel-brain.com/Reinforcement-Learning/) . This document contains information on functionally reusability, functional scalability and functional extensibility.\n\n### Problem Solution: [Generative Adversarial Networks Library: pygan](https://github.com/chimera0/accel-brain-code/tree/master/Generative-Adversarial-Networks)\n\n`pygan` is Python library to implement Generative Adversarial Networks(GANs) and Adversarial Auto-Encoders(AAEs).\n\nThis library makes it possible to design the Generative models based on the Statistical machine learning problems in relation to Generative Adversarial Networks(GANs) and Adversarial Auto-Encoders(AAEs) to practice algorithm design for semi-supervised learning.\n\nThe Generative Adversarial Networks(GANs) (Goodfellow et al., 2014) framework establishes a\nmin-max adversarial game between two neural networks – a generative model, `G`, and a discriminative\nmodel, `D`. The discriminator model, `D(x)`, is a neural network that computes the probability that\na observed data point `x` in data space is a sample from the data distribution (positive samples) that we are trying to model, rather than a sample from our generative model (negative samples). Concurrently, the generator uses a function `G(z)` that maps samples `z` from the prior `p(z)` to the data space. `G(z)` is trained to maximally confuse the discriminator into believing that samples it generates come from the data distribution. The generator is trained by leveraging the gradient of `D(x)` w.r.t. `x`, and using that to modify its parameters.\n\nThis library provides the Adversarial Auto-Encoders(AAEs), which is a probabilistic Auto-Encoder that uses GANs to perform variational inference by matching the aggregated posterior of the feature points in hidden layer of the Auto-Encoder with an arbitrary prior distribution(Makhzani, A., et al., 2015). Matching the aggregated posterior to the prior ensures that generating from any part of prior space results in meaningful samples. As a result, the decoder of the Adversarial Auto-Encoder learns a deep generative model that maps the imposed prior to the data distribution.\n\n#### Documentation\n\nFull documentation is available on [https://code.accel-brain.com/Generative-Adversarial-Networks/](https://code.accel-brain.com/Generative-Adversarial-Networks/) . This document contains information on functionally reusability, functional scalability and functional extensibility.\n\n### Problem Solution: [Algorithmic-Composition](https://github.com/chimera0/accel-brain-code/tree/master/Algorithmic-Composition)\n\n`pycomposer` is Python library for Algorithmic Composition or Automatic Composition by Reinforcement Learning such as Q-Learning and Recurrent Temporal Restricted Boltzmann Machine(RTRBM). Q-Learning and RTRBM in this library allows you to extract the melody information about a MIDI tracks and these models can learn and inference patterns of the melody. And This library has wrapper class for converting melody data inferenced by Q-Learning and RTRBM into MIDI file.\n\n#### Documentation\n\nFull documentation is available on [https://code.accel-brain.com/Algorithmic-Composition/](https://code.accel-brain.com/Algorithmic-Composition/). This document contains information on functionally reusability, functional scalability and functional extensibility.\n\n### Problem Solution: [Cardbox](https://github.com/chimera0/accel-brain-code/tree/master/Cardbox)\n\nThis is the simple card box system that make you able to find and save your ideas.\n\nYou can write down as many ideas as possible onto cards. Like the KJ Method or the mindmap tools, this simple JavaScript tool helps us to discover potential relations among the cards that you created. And the tagging function allow you to generate metadata of cards as to make their meaning and relationships understandable.\n\n### Problem Solution: [Binaural-Beat-and-Monaural-Beat-with-python](https://github.com/chimera0/accel-brain-code/tree/master/Binaural-Beat-and-Monaural-Beat-with-python)\n\n`AccelBrainBeat` is a Python library for creating the binaural beats or monaural beats. You can play these beats and generate wav files. The frequencys can be optionally selected.\n\nThis Python script enables you to handle your mind state by a kind of \"Brain-Wave Controller\" which is generally known as Biaural beat or Monauarl beats in a simplified method.\n\n#### Documentation\n\nFull documentation is available on [https://code.accel-brain.com/Binaural-Beat-and-Monaural-Beat-with-python/](https://code.accel-brain.com/Binaural-Beat-and-Monaural-Beat-with-python/) . This document contains information on functionally reusability, functional scalability and functional extensibility.\n\n### Problem Solution: [Binaural-Beat-and-Monaural-Beat-with-js](https://github.com/chimera0/accel-brain-code/tree/master/Binaural-Beat-and-Monaural-Beat-with-js)\n\nThese modules are functionally equivalent to Python Scripts in `AccelBrainBeat`.\n\n### Problem Solution: [Subliminal perception](https://github.com/chimera0/accel-brain-code/tree/master/Subliminal-Perception)\n\nThese JavaScript are tool for experimentation of subliminal perception.\n\nThis is a demo code for my case study in the context of my website.\n\n## References\n\nThe basic concepts, theories, and methods behind this library are described in the following books.\n\n\u003cdiv align=\"center\"\u003e\u003ca href=\"https://www.amazon.co.jp/dp/B08PV4ZQG5/\" target=\"_blank\"\u003e\u003cimg src=\"https://storage.googleapis.com/accel-brain-code/Accel-Brain-Books/In-house_R_and_D_in_the_era_of_democratization_of_AI/book_cover.jpg\" width=\"160px\" /\u003e\u003c/a\u003e\n  \u003cp\u003e『\u003ca href=\"https://www.amazon.co.jp/dp/B08PV4ZQG5/ref=sr_1_1?dchild=1\u0026qid=1607343553\u0026s=digital-text\u0026sr=1-1\u0026text=%E6%A0%AA%E5%BC%8F%E4%BC%9A%E7%A4%BEAccel+Brain\" target=\"_blank\"\u003e「AIの民主化」時代の企業内研究開発: 深層学習の「実学」としての機能分析\u003c/a\u003e』(Japanese)\u003c/p\u003e\u003c/div\u003e\n\n\u003cbr /\u003e\n  \n\u003cdiv align=\"center\"\u003e\u003ca href=\"https://www.amazon.co.jp/dp/B093Z533LK\" target=\"_blank\"\u003e\u003cimg src=\"https://storage.googleapis.com/accel-brain-code/Accel-Brain-Books/AI_vs_Investors_as_Noise_Traders/book_cover.jpg\" width=\"160px\" /\u003e\u003c/a\u003e\n  \u003cp\u003e『\u003ca href=\"https://www.amazon.co.jp/dp/B093Z533LK\" target=\"_blank\"\u003eAI vs. ノイズトレーダーとしての投資家たち: 「アルゴリズム戦争」時代の証券投資戦略\u003c/a\u003e』(Japanese)\u003c/p\u003e\u003c/div\u003e\n\n\u003cbr /\u003e\n\n\u003cdiv align=\"center\"\u003e\u003ca href=\"https://www.amazon.co.jp/dp/B0994CH3CM\" target=\"_blank\"\u003e\u003cimg src=\"https://storage.googleapis.com/accel-brain-code/Accel-Brain-Books/Babel_of_Natural_Language_Processing/book_cover.jpg\" width=\"160px\" /\u003e\u003c/a\u003e\n  \u003cp\u003e『\u003ca href=\"https://www.amazon.co.jp/dp/B0994CH3CM\" target=\"_blank\"\u003e自然言語処理のバベル: 文書自動要約、文章生成AI、チャットボットの意味論\u003c/a\u003e』(Japanese)\u003c/p\u003e\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\u003ca href=\"https://www.amazon.co.jp/dp/B09C4KYZBX\" target=\"_blank\"\u003e\u003cimg src=\"https://storage.googleapis.com/accel-brain-code/Accel-Brain-Books/Origin_of_the_statistical_machine_learning/book_cover.jpg\" width=\"160px\" /\u003e\u003c/a\u003e\n  \u003cp\u003e『\u003ca href=\"https://www.amazon.co.jp/dp/B09C4KYZBX\" target=\"_blank\"\u003e統計的機械学習の根源: 熱力学、量子力学、統計力学における天才物理学者たちの神学的な理念\u003c/a\u003e』(Japanese)\u003c/p\u003e\u003c/div\u003e\n  \n\u003cbr /\u003e\n\n\u003cdiv align=\"center\"\u003e\u003ca href=\"https://www.amazon.co.jp/dp/B09JC4Z7B4\" target=\"_blank\"\u003e\u003cimg border=\"0\" src=\"https://storage.googleapis.com/accel-brain-code/Accel-Brain-Books/Media_Aesthetics_of_Data_Visualization/book_cover.jpg\" width=\"160px\"\u003e\u003c/a\u003e\n  \u003cp\u003e『\u003ca href=\"https://www.amazon.co.jp/dp/B09JC4Z7B4\" target=\"_blank\"\u003eデータビジュアライゼーションのメディア美学: ハイブリッド戦略の魔術師たち\u003c/a\u003e』(Japanese)\u003c/p\u003e\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\u003ca href=\"https://www.amazon.co.jp/dp/B09P4JXQWB\" target=\"_blank\"\u003e\u003cimg border=\"0\" src=\"https://storage.googleapis.com/accel-brain-code/Accel-Brain-Books/Education_of_the_Faustian_man/book_cover.jpg\" width=\"160px\"\u003e\u003c/a\u003e\n  \u003cp\u003e『\u003ca href=\"https://www.amazon.co.jp/dp/B09P4JXQWB\" target=\"_blank\"\u003e「ファウスト的人間」の教育: 起業家精神の生涯学習\u003c/a\u003e』(Japanese)\u003c/p\u003e\u003c/div\u003e\n\n## Author\n\n- Accel Brain Co., Ltd.\n\n## Author URI\n\n- http://accel-brain.com/\n- http://accel-brain.co.jp/\n\n## License\n\n- GNU General Public License v2.0\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faccel-brain%2Faccel-brain-code","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faccel-brain%2Faccel-brain-code","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faccel-brain%2Faccel-brain-code/lists"}