{
    "componentChunkName": "component---src-templates-note-note-js",
    "path": "/notes/Long-Short-Term-Memory",
    "result": {"data":{"mdx":{"body":"var _excluded = [\"components\"];\nfunction _extends() { _extends = Object.assign ? Object.assign.bind() : function (target) { for (var i = 1; i < arguments.length; i++) { var source = arguments[i]; for (var key in source) { if (Object.prototype.hasOwnProperty.call(source, key)) { target[key] = source[key]; } } } return target; }; return _extends.apply(this, arguments); }\nfunction _objectWithoutProperties(source, excluded) { if (source == null) return {}; var target = _objectWithoutPropertiesLoose(source, excluded); var key, i; if (Object.getOwnPropertySymbols) { var sourceSymbolKeys = Object.getOwnPropertySymbols(source); for (i = 0; i < sourceSymbolKeys.length; i++) { key = sourceSymbolKeys[i]; if (excluded.indexOf(key) >= 0) continue; if (!Object.prototype.propertyIsEnumerable.call(source, key)) continue; target[key] = source[key]; } } return target; }\nfunction _objectWithoutPropertiesLoose(source, excluded) { if (source == null) return {}; var target = {}; var sourceKeys = Object.keys(source); var key, i; for (i = 0; i < sourceKeys.length; i++) { key = sourceKeys[i]; if (excluded.indexOf(key) >= 0) continue; target[key] = source[key]; } return target; }\n/* @jsxRuntime classic */\n/* @jsx mdx */\n\nvar _frontmatter = {\n  \"aliases\": [\"LSTM\"]\n};\nvar layoutProps = {\n  _frontmatter: _frontmatter\n};\nvar MDXLayout = \"wrapper\";\nreturn function MDXContent(_ref) {\n  var components = _ref.components,\n    props = _objectWithoutProperties(_ref, _excluded);\n  return mdx(MDXLayout, _extends({}, layoutProps, props, {\n    components: components,\n    mdxType: \"MDXLayout\"\n  }), mdx(\"blockquote\", null, mdx(\"p\", {\n    parentName: \"blockquote\"\n  }, \"BPTT is the key algorithm that enables RNNs and related models to learn from sequences by propagating error gradients back through time, capturing the temporal structure inherent in many AI applications dealing with sequential data.\")), mdx(\"p\", null, \"LSTM stands for Long Short-Term Memory, which is a type of recurrent neural network (RNN) architecture used in the field of deep learning. LSTMs are designed to model sequences and time series data, making them particularly effective for tasks where \", mdx(\"a\", {\n    parentName: \"p\",\n    \"href\": \"/notes/context-and-order\",\n    \"title\": \"context and order\"\n  }, \"context and order\"), \" are important, such as natural language processing, speech recognition, and time series prediction.\"), mdx(\"p\", null, \"\", mdx(\"a\", {\n    parentName: \"p\",\n    \"href\": \"/notes/The-key-feature-of-LSTMs-is-their-ability-to-maintain-long-term-dependencies-in-the-data\",\n    \"title\": \"The key feature of LSTMs is their ability to maintain long-term dependencies in the data\"\n  }, \"The key feature of LSTMs is their ability to maintain long-term dependencies in the data\"), \". They achieve this through a special structure called a memory cell, which can store information for long periods. LSTMs use three main gates\\u2014input, output, and \", mdx(\"a\", {\n    parentName: \"p\",\n    \"href\": \"/notes/forget-gates\",\n    \"title\": \"forget gates\"\n  }, \"forget gates\"), \" \\u2014to control the flow of information into and out of the memory cell, allowing them to learn which information to keep or discard over time. This makes them more effective than traditional RNNs in handling the \", mdx(\"a\", {\n    parentName: \"p\",\n    \"href\": \"/notes/vanishing-gradient-problem\",\n    \"title\": \"vanishing gradient problem\"\n  }, \"vanishing gradient problem\"), \", which can occur when \", mdx(\"a\", {\n    parentName: \"p\",\n    \"href\": \"/notes/training-deep-networks\",\n    \"title\": \"training deep networks\"\n  }, \"training deep networks\"), \".\"));\n}\n;\nMDXContent.isMDXComponent = true;","inboundReferences":[]}},"pageContext":{"slug":"Long-Short-Term-Memory","node":{"childMdx":{"slug":"Long-Short-Term-Memory"}}}},
    "staticQueryHashes": []}