{
    "info": {
        "author": "Archie Shahidullah",
        "author_email": "archie@caltech.edu",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Developers",
            "Intended Audience :: Education",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: Apache Software License",
            "Programming Language :: Python :: 3.6",
            "Topic :: Scientific/Engineering",
            "Topic :: Scientific/Engineering :: Artificial Intelligence",
            "Topic :: Software Development",
            "Topic :: Software Development :: Libraries",
            "Topic :: Software Development :: Libraries :: Python Modules"
        ],
        "description": "# GliaML\n\nGliaML is simple, yet powerful machine learning library written in Python.\n\nCurrently, it allows a user to easily create a multi-layer perceptron neural network with\nthe following features:\n\n1. Allow backpropagation with the sigmoid, tanh, and ReLU activation functions.\n2. Allow normalisation of a classifier with the softmax function.\n3. Allow learning rate hyperparameter functionality (including biases)\n4. Allow L2 regularisation to prevent over-fitting\n\n## Creating a Network\n\nIn GliaML, neural networks are implemented as objects containing a collection of layers,\nwhich are in turn objects. To create a layer, first a list of activation functions for \neach neuron in the list must be chosen. Then the layer can be created. Bias functionality\ncan be \n\n    activations1 = [activation_id for i in range(0, num_neurons)]\n    layer1 = NetworkLayer(num_inputs, num_neurons, activations1, bias=False)\n\nAfter a satisfactory number of layers have been created, the neural network itself can be \ninvoked by calling the constructor and providing all the layers. If \n\n    network = NeuralNetwork(l2_regularization=0.03, layer1, layer2, ...) \n\n## Training a network\n\nAfter creating your network, you'll want to provide training and testing data. These should\nbe formatted as NumPy arrays. For example, let us consider the following training set.\n\n    training_inputs = np.array([[1, 0, 1], [0, 0, 1], [1, 1, 0], [0, 1, 0]])\n    training_outputs = np.array([[1, 1, 0, 0]]).T\n\nThe solution is whether or not there is a 1 or 0 in the 3rd place of the input array. We now\nneed to train the network. We can either use mean-squared error or cross-entropy loss.\n\n    network.train_mean_squared_error(training_inputs, training_outputs, num_iterations, \n                                     learning_rate=0.05, bias_learning_rate=0.05)\n\nWe can now see the network's response on a problem it hasn't seen before.\n\n    answer = network.think(np.array([1, 1, 1]))\n    print(answer[-1])\n\nSee [example.py](https://github.com/Archiecool4/GliaML/blob/master/example.py) for another\nusage example.\n\n",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "https://github.com/Archiecool4/GliaML",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/Archiecool4/GliaML",
        "keywords": "machine learning neural networks",
        "license": "http://www.apache.org/licenses/LICENSE-2.0",
        "maintainer": "",
        "maintainer_email": "",
        "name": "gliaml",
        "package_url": "https://pypi.org/project/gliaml/",
        "platform": "",
        "project_url": "https://pypi.org/project/gliaml/",
        "project_urls": {
            "Download": "https://github.com/Archiecool4/GliaML",
            "Homepage": "https://github.com/Archiecool4/GliaML"
        },
        "release_url": "https://pypi.org/project/gliaml/0.1.1/",
        "requires_dist": [
            "numpy"
        ],
        "requires_python": "",
        "summary": "GliaML - Python Machine Learning Library",
        "version": "0.1.1"
    },
    "last_serial": 4966521,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "b77e3f768dead55d4ad64b8688b22cd6",
                    "sha256": "dbd17fc4353e4f8ed3fba7de1006dd107b210a3f86a2610e34a28aae657c1b12"
                },
                "downloads": -1,
                "filename": "gliaml-0.0.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "b77e3f768dead55d4ad64b8688b22cd6",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 9472,
                "upload_time": "2019-03-18T04:54:35",
                "url": "https://files.pythonhosted.org/packages/2f/d3/39877d5b91e27db882b92b6764fb6ef2493cdb4933e0912561c40e5a0ecf/gliaml-0.0.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "002d5bc821c13f6560767d9c0737f2ba",
                    "sha256": "bdf6d7e511cb290a1808921fb4233127029c6793763403520dcd2f4435e88199"
                },
                "downloads": -1,
                "filename": "gliaml-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "002d5bc821c13f6560767d9c0737f2ba",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8219,
                "upload_time": "2019-03-18T04:54:37",
                "url": "https://files.pythonhosted.org/packages/e2/7a/f0b7b56ebe835b6ad499f7061da71376af73f254088e7ce2e61b053c9726/gliaml-0.0.1.tar.gz"
            }
        ],
        "0.0.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "46f14a6a70913de09192536e14c18131",
                    "sha256": "d6f99ec51a8f234e5f5d2b3589dcb1447a10d3ca8beff6c13bee929c21d11e8c"
                },
                "downloads": -1,
                "filename": "gliaml-0.0.2-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "46f14a6a70913de09192536e14c18131",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 13314,
                "upload_time": "2019-03-18T05:11:55",
                "url": "https://files.pythonhosted.org/packages/ff/a2/ea75b59943718b585b0506ea2a9e737ea9264dc27053cc863105b7a81c26/gliaml-0.0.2-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "a05792662279b97226a3f7572f62d9fa",
                    "sha256": "99de2e81bec25122e4a3050a56462b10d538f839ced573fe3f9ad54469917725"
                },
                "downloads": -1,
                "filename": "gliaml-0.0.2.tar.gz",
                "has_sig": false,
                "md5_digest": "a05792662279b97226a3f7572f62d9fa",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7864,
                "upload_time": "2019-03-18T05:11:57",
                "url": "https://files.pythonhosted.org/packages/d1/be/e2b4dcf6efff599fb5288640734c3f9f0a093bd62b89f895de1687682613/gliaml-0.0.2.tar.gz"
            }
        ],
        "0.0.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "a3d5d97613e717951a4d8ac3c0ad822a",
                    "sha256": "c83dbc1a99645673444fa5b4d97b4635b2bfeac72cd378d1ef296477dfbcf32c"
                },
                "downloads": -1,
                "filename": "gliaml-0.0.3-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "a3d5d97613e717951a4d8ac3c0ad822a",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 13313,
                "upload_time": "2019-03-18T05:18:39",
                "url": "https://files.pythonhosted.org/packages/e5/51/63839d13d7bada5bc5a57023b59730103316fb2027910c7ffaafe2e7e9b5/gliaml-0.0.3-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "e71d6bf0a3386b36c8dedf6db5f7b84d",
                    "sha256": "9257d367fdc18f52b64af842d2d464f377904faceff6937de7b0a2296e0d3f2f"
                },
                "downloads": -1,
                "filename": "gliaml-0.0.3.tar.gz",
                "has_sig": false,
                "md5_digest": "e71d6bf0a3386b36c8dedf6db5f7b84d",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7869,
                "upload_time": "2019-03-18T05:18:41",
                "url": "https://files.pythonhosted.org/packages/5f/61/3a918479b1d9951403af668c83689b6a3ab136e7f4e6c79d0bbe9faa7475/gliaml-0.0.3.tar.gz"
            }
        ],
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "ab88560b0f89a6f639508d5365a7fd33",
                    "sha256": "af3b1279a67aae52d5d0e74d1e72decb5c61df53c1617d743a6966b753b985f5"
                },
                "downloads": -1,
                "filename": "gliaml-0.1.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "ab88560b0f89a6f639508d5365a7fd33",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 14304,
                "upload_time": "2019-03-21T04:02:22",
                "url": "https://files.pythonhosted.org/packages/c2/f5/f9b3cfb07ff6a946242954b707ff3cae0e4117c33c223e4fa61ef538a972/gliaml-0.1.0-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "3ddce28cbf7e35b298b9ddd2cdc71f49",
                    "sha256": "a6206177cfeb1aabe7844f5ee7166970d4fb791f853e0e2a34832c4766d7fd56"
                },
                "downloads": -1,
                "filename": "gliaml-0.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "3ddce28cbf7e35b298b9ddd2cdc71f49",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8934,
                "upload_time": "2019-03-21T04:02:26",
                "url": "https://files.pythonhosted.org/packages/ef/3f/c5b4be2a2800481c473eef3c2736fcbea51c08db25db69929824155ca625/gliaml-0.1.0.tar.gz"
            }
        ],
        "0.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "4962f8a1603aea2991240cc93b886783",
                    "sha256": "12581378affa28b4966f8e07fab5f1cb19e689c33fbb50e25b7ee2e9eb42b94a"
                },
                "downloads": -1,
                "filename": "gliaml-0.1.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "4962f8a1603aea2991240cc93b886783",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 14306,
                "upload_time": "2019-03-21T04:15:41",
                "url": "https://files.pythonhosted.org/packages/87/7c/250032b26ca764b619045644e315f69026500df88f6cd0650368e2040a44/gliaml-0.1.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "ab8e81e960dc7f6518a80aad49fcbca8",
                    "sha256": "08baf41c63529575e579361dc25deab3386f73b3874ead4391a86f6ad3e57d7b"
                },
                "downloads": -1,
                "filename": "gliaml-0.1.1.tar.gz",
                "has_sig": false,
                "md5_digest": "ab8e81e960dc7f6518a80aad49fcbca8",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 8932,
                "upload_time": "2019-03-21T04:15:45",
                "url": "https://files.pythonhosted.org/packages/e9/1a/ffa469d9cd292652fac1c420c227914e14f4dfd4b03c2a31366608c08063/gliaml-0.1.1.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "4962f8a1603aea2991240cc93b886783",
                "sha256": "12581378affa28b4966f8e07fab5f1cb19e689c33fbb50e25b7ee2e9eb42b94a"
            },
            "downloads": -1,
            "filename": "gliaml-0.1.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "4962f8a1603aea2991240cc93b886783",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 14306,
            "upload_time": "2019-03-21T04:15:41",
            "url": "https://files.pythonhosted.org/packages/87/7c/250032b26ca764b619045644e315f69026500df88f6cd0650368e2040a44/gliaml-0.1.1-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "ab8e81e960dc7f6518a80aad49fcbca8",
                "sha256": "08baf41c63529575e579361dc25deab3386f73b3874ead4391a86f6ad3e57d7b"
            },
            "downloads": -1,
            "filename": "gliaml-0.1.1.tar.gz",
            "has_sig": false,
            "md5_digest": "ab8e81e960dc7f6518a80aad49fcbca8",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 8932,
            "upload_time": "2019-03-21T04:15:45",
            "url": "https://files.pythonhosted.org/packages/e9/1a/ffa469d9cd292652fac1c420c227914e14f4dfd4b03c2a31366608c08063/gliaml-0.1.1.tar.gz"
        }
    ]
}