{"id":146665,"date":"2025-08-22T12:25:42","date_gmt":"2025-08-22T06:55:42","guid":{"rendered":"https:\/\/data-flair.training\/blogs\/?p=146665"},"modified":"2025-08-22T12:25:42","modified_gmt":"2025-08-22T06:55:42","slug":"handwritten-digit-recognition-using-ann","status":"publish","type":"post","link":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/","title":{"rendered":"Deep Learning Project &#8211; Handwritten Digit Recognition using ANN"},"content":{"rendered":"<h3>Program 1<\/h3>\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"generic\">Handwritten Digit Recognition with ANN\r\n\r\nTo build a machine learning model using an Artificial Neural Network (ANN) that can accurately classify handwritten digits (0\u20139) from grayscale images of size 28\u00d728 pixels.\r\n\r\nDataset : MNIST  (60 000 train images \/ 10 000 test images)\r\nGoal    : Classify digits 0\u20139 from 28\u00d728 grayscale images\r\nModel   : Simple feed-forward neural network (Dense layers)\r\n\r\n# 1. Imports\r\nimport numpy as np\r\nimport matplotlib.pyplot as plt\r\nfrom tensorflow.keras.datasets import mnist\r\nfrom tensorflow.keras.models import Sequential\r\nfrom tensorflow.keras.layers import Flatten, Dense, Dropout\r\nfrom tensorflow.keras.utils import to_categorical\r\nfrom sklearn.metrics import classification_report, confusion_matrix\r\nimport seaborn as sns`\r\n\r\n# 2. Load the MNIST data\r\n# X_train: 60,000 training images\r\n# y_train: their correct labels\r\n# X_test: 10,000 test images\r\n# y_test: their labels\r\n(X_train, y_train), (X_test, y_test) = mnist.load_data()   # shape (60000, 28, 28), (10000, 28, 28)\r\nlen(X_test)\r\n\r\n# 3. Normalise pixel values (0-255 \u279c 0-1)\r\n# Each pixel value is between 0 and 255.\r\n# We scale them to 0\u20131 range, which makes training easier.\r\n\r\nX_train = X_train.astype(\"float32\") \/ 255.0\r\nX_test  = X_test.astype(\"float32\")  \/ 255.0\r\ny_train\r\n\r\n# 4. Convert labels to one-hot vectors\r\n #Converts labels (0\u20139) into 10-element vectors for softmax.\r\n# Instead of labels like 3 or 9, we convert them to vectors like:\r\n# Label 3 \u2192 [0, 0, 0, 1, 0, 0, 0, 0, 0, 0]\r\n# This is needed for multi-class classification.\r\n\r\nnum_classes = 10\r\ny_train_cat = to_categorical(y_train, num_classes)\r\ny_test_cat  = to_categorical(y_test,  num_classes)\r\ny_test_cat\r\n\r\n# 5. Build the ANN model\r\n# Flatten: Converts 28\u00d728 image into a long row (784 pixels).\r\n# Dense(256): First layer with 256 neurons \u2192 learns patterns.\r\n# Dense(128): Second layer with 64 neurons \u2192 deeper learning.\r\n# Dense(10): Output layer with 10 neurons (for 10 classes).\r\n# softmax helps pick the best class.\r\n\r\nmodel = Sequential([\r\n    Flatten(input_shape=(28, 28)),      # 28\u00d728 \u279c 784-vector\r\n    Dense(256, activation=\"relu\"),\r\n    Dropout(0.3),\r\n    Dense(128, activation=\"relu\"),\r\n    Dropout(0.3),\r\n    Dense(num_classes, activation=\"softmax\")   # 10 output neurons\r\n])\r\n\r\n# 6. Compile the model\r\nmodel.compile(\r\n    optimizer=\"adam\",\r\n    loss=\"categorical_crossentropy\",\r\n    metrics=[\"accuracy\"]\r\n)\r\nmodel.summary()\r\n\r\n# 7. Train the model\r\nhistory = model.fit(\r\n    X_train, y_train_cat,\r\n    epochs=15,\r\n    batch_size=128,\r\n    validation_split=0.1,\r\n    verbose=1\r\n)\r\n\r\n# 8. Evaluate on the test set\r\ntest_loss, test_acc = model.evaluate(X_test, y_test_cat, verbose=0)\r\nprint(f\"\\nTest accuracy: {test_acc*100:.2f}%\")\r\n\r\n# 9. Generate predictions\r\ny_pred_probs = model.predict(X_test)\r\ny_pred = np.argmax(y_pred_probs, axis=1)\r\n\r\nprint(\"\\nClassification Report:\")\r\nprint(classification_report(y_test, y_pred))\r\n\r\n# 10. Confusion matrix\r\ncm = confusion_matrix(y_test, y_pred)\r\nplt.figure(figsize=(8,6))\r\nsns.heatmap(cm, annot=True, fmt=\"d\", cmap=\"Blues\")\r\nplt.title(\"MNIST Confusion Matrix\")\r\nplt.xlabel(\"Predicted\")\r\nplt.ylabel(\"Actual\")\r\nplt.tight_layout()\r\nplt.show()\r\n\r\n# 11. Display a handful of predictions\r\nplt.figure(figsize=(10,4))\r\nfor i in range(10):\r\n    idx = np.random.randint(0, len(X_test))\r\n    img = X_test[idx]\r\n    true_digit = y_test[idx]\r\n    pred_digit = y_pred[idx]\r\n    color = \"green\" if true_digit == pred_digit else \"red\"\r\n\r\n    plt.subplot(2, 5, i+1)\r\n    plt.imshow(img, cmap=\"gray\")\r\n    plt.title(f\"T:{true_digit} P:{pred_digit}\", color=color, fontsize=10)\r\n    plt.axis(\"off\")\r\n\r\nplt.tight_layout()\r\nplt.show()\r\n<\/pre>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Program 1 Handwritten Digit Recognition with ANN To build a machine learning model using an Artificial Neural Network (ANN) that can accurately classify handwritten digits (0\u20139) from grayscale images of size 28\u00d728 pixels. Dataset&#46;&#46;&#46;<\/p>\n","protected":false},"author":581,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[36],"tags":[21661,35126,35128,35127,35129,8431,33127,33128,20697],"class_list":["post-146665","post","type-post","status-publish","format-standard","hentry","category-machine-learning","tag-handwritten-digit-recognition","tag-handwritten-digit-recognition-using-ann","tag-handwritten-digit-recognition-using-deep-learning","tag-handwritten-digit-recognition-using-machine-learning","tag-handwritten-digit-recognition-using-neural-network","tag-machine-learning","tag-machine-learning-practical","tag-machine-learning-program","tag-machine-learning-project"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Deep Learning Project - Handwritten Digit Recognition using ANN - DataFlair<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Deep Learning Project - Handwritten Digit Recognition using ANN - DataFlair\" \/>\n<meta property=\"og:description\" content=\"Program 1 Handwritten Digit Recognition with ANN To build a machine learning model using an Artificial Neural Network (ANN) that can accurately classify handwritten digits (0\u20139) from grayscale images of size 28\u00d728 pixels. Dataset&#046;&#046;&#046;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/\" \/>\n<meta property=\"og:site_name\" content=\"DataFlair\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DataFlairWS\/\" \/>\n<meta property=\"article:published_time\" content=\"2025-08-22T06:55:42+00:00\" \/>\n<meta name=\"author\" content=\"DataFlair Team\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DataFlairWS\" \/>\n<meta name=\"twitter:site\" content=\"@DataFlairWS\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"DataFlair Team\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Deep Learning Project - Handwritten Digit Recognition using ANN - DataFlair","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/","og_locale":"en_US","og_type":"article","og_title":"Deep Learning Project - Handwritten Digit Recognition using ANN - DataFlair","og_description":"Program 1 Handwritten Digit Recognition with ANN To build a machine learning model using an Artificial Neural Network (ANN) that can accurately classify handwritten digits (0\u20139) from grayscale images of size 28\u00d728 pixels. Dataset&#46;&#46;&#46;","og_url":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/","og_site_name":"DataFlair","article_publisher":"https:\/\/www.facebook.com\/DataFlairWS\/","article_published_time":"2025-08-22T06:55:42+00:00","author":"DataFlair Team","twitter_card":"summary_large_image","twitter_creator":"@DataFlairWS","twitter_site":"@DataFlairWS","twitter_misc":{"Written by":"DataFlair Team","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/#article","isPartOf":{"@id":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/"},"author":{"name":"DataFlair Team","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/person\/c187795dc82ab948373cca526df7c445"},"headline":"Deep Learning Project &#8211; Handwritten Digit Recognition using ANN","datePublished":"2025-08-22T06:55:42+00:00","mainEntityOfPage":{"@id":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/"},"wordCount":11,"commentCount":0,"publisher":{"@id":"https:\/\/data-flair.training\/blogs\/#organization"},"keywords":["Handwritten digit recognition","handwritten digit recognition using ann","handwritten digit recognition using deep learning","handwritten digit recognition using machine learning","handwritten digit recognition using neural network","machine learning","machine learning practical","machine learning program","machine learning project"],"articleSection":["Machine Learning Tutorials"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/","url":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/","name":"Deep Learning Project - Handwritten Digit Recognition using ANN - DataFlair","isPartOf":{"@id":"https:\/\/data-flair.training\/blogs\/#website"},"datePublished":"2025-08-22T06:55:42+00:00","breadcrumb":{"@id":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/data-flair.training\/blogs\/handwritten-digit-recognition-using-ann\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Blog Home","item":"https:\/\/data-flair.training\/blogs\/"},{"@type":"ListItem","position":2,"name":"Machine Learning Tutorials","item":"https:\/\/data-flair.training\/blogs\/category\/machine-learning\/"},{"@type":"ListItem","position":3,"name":"Deep Learning Project &#8211; Handwritten Digit Recognition using ANN"}]},{"@type":"WebSite","@id":"https:\/\/data-flair.training\/blogs\/#website","url":"https:\/\/data-flair.training\/blogs\/","name":"DataFlair","description":"Learn Today. Lead Tomorrow.","publisher":{"@id":"https:\/\/data-flair.training\/blogs\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/data-flair.training\/blogs\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/data-flair.training\/blogs\/#organization","name":"DataFlair","url":"https:\/\/data-flair.training\/blogs\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/logo\/image\/","url":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2016\/07\/Data-Flair.png","contentUrl":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2016\/07\/Data-Flair.png","width":106,"height":48,"caption":"DataFlair"},"image":{"@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DataFlairWS\/","https:\/\/x.com\/DataFlairWS","https:\/\/www.linkedin.com\/company\/dataflair-web-services-pvt-ltd\/","https:\/\/www.youtube.com\/user\/DataFlairWS"]},{"@type":"Person","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/person\/c187795dc82ab948373cca526df7c445","name":"DataFlair Team","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/2302ebc438084d2f1f993edc1996a0aae01332e81f3227cba8df0c48ec010ca4?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/2302ebc438084d2f1f993edc1996a0aae01332e81f3227cba8df0c48ec010ca4?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/2302ebc438084d2f1f993edc1996a0aae01332e81f3227cba8df0c48ec010ca4?s=96&d=mm&r=g","caption":"DataFlair Team"},"description":"DataFlair Team provides high-impact content on programming, Java, Python, C++, DSA, AI, ML, data Science, Android, Flutter, MERN, Web Development, and technology. We make complex concepts easy to grasp, helping learners of all levels succeed in their tech careers.","url":"https:\/\/data-flair.training\/blogs\/author\/dfteam6\/"}]}},"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/146665","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/users\/581"}],"replies":[{"embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/comments?post=146665"}],"version-history":[{"count":3,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/146665\/revisions"}],"predecessor-version":[{"id":146683,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/146665\/revisions\/146683"}],"wp:attachment":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/media?parent=146665"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/categories?post=146665"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/tags?post=146665"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}