{"id":278,"date":"2025-11-06T03:48:17","date_gmt":"2025-11-06T03:48:17","guid":{"rendered":"https:\/\/binus.ac.id\/humanitarian-ai\/?p=278"},"modified":"2026-02-04T06:19:06","modified_gmt":"2026-02-04T06:19:06","slug":"python-programming-for-deep-learning","status":"publish","type":"post","link":"https:\/\/binus.ac.id\/humanitarian-ai\/blog\/2025\/11\/06\/python-programming-for-deep-learning\/","title":{"rendered":"Python Programming for Deep Learning"},"content":{"rendered":"<h1 style=\"text-align: center\" data-start=\"326\" data-end=\"342\"><span style=\"font-size: 18pt\">Training Syllabus<\/span><\/h1>\n<h4 data-start=\"1783\" data-end=\"1799\">\ud83d\udd58 Duration: <strong>4\u00a0full days<\/strong> (08:00 AM \u2013 04:00 PM GMT+7)<\/h4>\n<h4 data-start=\"1845\" data-end=\"1873\">\ud83d\udc65 Minimum Participants: <strong data-start=\"1874\" data-end=\"1886\">5 people<\/strong><\/h4>\n<h4 data-start=\"1888\" data-end=\"1899\">\ud83d\udcbc Fee: <strong data-start=\"1900\" data-end=\"1932\">Based on agreement and venue<\/strong><\/h4>\n<hr class=\"\" data-start=\"1934\" data-end=\"1937\" \/>\n<h3 class=\"\" data-start=\"1939\" data-end=\"1967\">\ud83d\udccb <strong data-start=\"1946\" data-end=\"1967\">Training Overview<\/strong><\/h3>\n<pre id=\"tw-target-text\" class=\"tw-data-text tw-text-large tw-ta\" dir=\"ltr\" role=\"text\" data-placeholder=\"Translation\" data-ved=\"2ahUKEwjrz66qzNyQAxVgTGwGHbaxAKwQ3ewLegQIChAV\" aria-label=\"Translated text: This Python Programming for Deep Learning training is designed for participants who already understand the basics of Python and want to delve deeper into the world of artificial intelligence (AI), specifically deep learning. Participants will learn how Python is used to build, train, and evaluate neural network models using modern libraries like TensorFlow and Keras. This training focuses on hands-on coding and real-world case studies, enabling participants to understand the deep learning workflow, from data preprocessing and model architecture to training and evaluation.\"><span class=\"Y2IQFc\" lang=\"en\">This <strong>Python Programming for Deep Learning<\/strong> training is designed for participants who already understand the basics of Python and want to delve deeper into the world of artificial intelligence (AI), specifically deep learning. Participants will learn how Python is used to build, train, and evaluate neural network models using modern libraries like TensorFlow and Keras.\r\nThis training focuses on hands-on coding and real-world case studies, enabling participants to understand the deep learning workflow, from data preprocessing and model architecture to training and evaluation. <a href=\"https:\/\/binus.ac.id\/humanitarian-ai\/wp-content\/uploads\/2025\/11\/Python-Programming-for-Deep-Learning-2.pdf\">Download sylabus<\/a>.<\/span><\/pre>\n<hr class=\"\" data-start=\"2415\" data-end=\"2418\" \/>\n<h3 class=\"\" data-start=\"2420\" data-end=\"2445\">\ud83d\udcda <strong data-start=\"2427\" data-end=\"2445\">Topics Covered<\/strong><\/h3>\n<p><strong>Session 1 \u2013 Introduction to Deep Learning and the Environment<\/strong><\/p>\n<ul>\n<li data-start=\"2420\" data-end=\"2445\">A Brief Overview of Python and Numpy.<\/li>\n<li data-start=\"2420\" data-end=\"2445\">Machine Learning vs. Deep Learning Concepts.<\/li>\n<li data-start=\"2420\" data-end=\"2445\">Neural Network Architecture.<\/li>\n<li data-start=\"2420\" data-end=\"2445\">Installing and Setting Up TensorFlow\/Keras.<\/li>\n<li data-start=\"2420\" data-end=\"2445\">Hands-on.<\/li>\n<\/ul>\n<p><strong>Session 2 \u2013 Data Preparation and Manipulation for Deep Learning <\/strong><\/p>\n<ul>\n<li id=\"tw-target-text\" class=\"tw-data-text tw-text-large tw-ta\" dir=\"ltr\" role=\"text\" data-placeholder=\"Translation\" data-ved=\"2ahUKEwi7u967zdyQAxXvXGwGHVn2CaUQ3ewLegQIChAV\" aria-label=\"Translated text: \u2022 Data loading and preprocessing (normalization, one-hot encoding) \u2022 Data splitting: training, validation, testing \u2022 Using Pandas and scikit-learn for the data pipeline \u2022 Data distribution visualization with Matplotlib\/Seaborn \u2022 Hands-on: MNIST dataset and initial analysis\"><span class=\"Y2IQFc\" lang=\"en\">Data loading and preprocessing (normalization, one-hot encoding)<\/span><\/li>\n<li class=\"tw-data-text tw-text-large tw-ta\" dir=\"ltr\" role=\"text\" data-placeholder=\"Translation\" data-ved=\"2ahUKEwi7u967zdyQAxXvXGwGHVn2CaUQ3ewLegQIChAV\" aria-label=\"Translated text: \u2022 Data loading and preprocessing (normalization, one-hot encoding) \u2022 Data splitting: training, validation, testing \u2022 Using Pandas and scikit-learn for the data pipeline \u2022 Data distribution visualization with Matplotlib\/Seaborn \u2022 Hands-on: MNIST dataset and initial analysis\"><span class=\"Y2IQFc\" lang=\"en\">Data splitting: training, validation, testing <\/span><\/li>\n<li class=\"tw-data-text tw-text-large tw-ta\" dir=\"ltr\" role=\"text\" data-placeholder=\"Translation\" data-ved=\"2ahUKEwi7u967zdyQAxXvXGwGHVn2CaUQ3ewLegQIChAV\" aria-label=\"Translated text: \u2022 Data loading and preprocessing (normalization, one-hot encoding) \u2022 Data splitting: training, validation, testing \u2022 Using Pandas and scikit-learn for the data pipeline \u2022 Data distribution visualization with Matplotlib\/Seaborn \u2022 Hands-on: MNIST dataset and initial analysis\"><span class=\"Y2IQFc\" lang=\"en\">Using Pandas and scikit-learn for the data pipeline <\/span><\/li>\n<li class=\"tw-data-text tw-text-large tw-ta\" dir=\"ltr\" role=\"text\" data-placeholder=\"Translation\" data-ved=\"2ahUKEwi7u967zdyQAxXvXGwGHVn2CaUQ3ewLegQIChAV\" aria-label=\"Translated text: \u2022 Data loading and preprocessing (normalization, one-hot encoding) \u2022 Data splitting: training, validation, testing \u2022 Using Pandas and scikit-learn for the data pipeline \u2022 Data distribution visualization with Matplotlib\/Seaborn \u2022 Hands-on: MNIST dataset and initial analysis\"><span class=\"Y2IQFc\" lang=\"en\">Data distribution visualization with Matplotlib\/Seaborn <\/span><\/li>\n<li class=\"tw-data-text tw-text-large tw-ta\" dir=\"ltr\" role=\"text\" data-placeholder=\"Translation\" data-ved=\"2ahUKEwi7u967zdyQAxXvXGwGHVn2CaUQ3ewLegQIChAV\" aria-label=\"Translated text: \u2022 Data loading and preprocessing (normalization, one-hot encoding) \u2022 Data splitting: training, validation, testing \u2022 Using Pandas and scikit-learn for the data pipeline \u2022 Data distribution visualization with Matplotlib\/Seaborn \u2022 Hands-on: MNIST dataset and initial analysis\"><span class=\"Y2IQFc\" lang=\"en\">Hands-on: MNIST dataset and initial analysis<\/span><\/li>\n<\/ul>\n<p><strong>Session 3 \u2013 Builidng and Training Neural Network<\/strong><\/p>\n<ul>\n<li>Konsep layer, neuron, activation function, loss, dan optimizer<\/li>\n<li>Backpropagation dan gradient descent (konsep intuitif)<\/li>\n<li>Implementasi model DNN (Fully Connected Network)<\/li>\n<li>Evaluasi model: accuracy, loss curve<\/li>\n<li>Hands-on: Membangun model klasifikasi digit (MNIST)<\/li>\n<\/ul>\n<p><strong>Session 4 \u2013 Convolutional Neural Network (CNN) for Image Data<\/strong><\/p>\n<ul>\n<li>Convolution, pooling and filter concept.<\/li>\n<li>Popular CNN Architectures.<\/li>\n<li>Implementing CNN with Keras.<\/li>\n<li>Data Augmentation for improving performance.<\/li>\n<li>Hands-on: Image Classification.<\/li>\n<\/ul>\n<p><strong>Session 5 \u2013 Recurrent Neural Network (RNN) and LSTM for Sequential Data<\/strong><\/p>\n<ul>\n<li>Sequence data concept and temporal dependencies.<\/li>\n<li>\u00a0RNN architecture and LSTM.<\/li>\n<li>RNN\/LSTM implementation with Keras.<\/li>\n<li>Case study: simple text sentiment analysis.<\/li>\n<li>Hands-on: Text prediction.<\/li>\n<\/ul>\n<p><strong>Session 6 \u2013 Optimization and Model Evaluation<\/strong><\/p>\n<ul>\n<li>Overfitting vs underfitting.<\/li>\n<li>Regularization (Dropout, Early Stopping).<\/li>\n<li>Hyperparameter tuning.<\/li>\n<li>Model evaluation dan confusion matrix.<\/li>\n<li>Hands-on: Improving performance model of\u00a0 CNN.<\/li>\n<\/ul>\n<p><strong>Session 7 \u2013 Transfer Learning and Fine-Tuning<\/strong><\/p>\n<ul>\n<li>Transfer learning concept.<\/li>\n<li>Using pre-trained model (MobileNet, ResNet, EfficientNet).<\/li>\n<li>Fine-tuning for custome dataset.<\/li>\n<li>Hands-on: image classification with transfer learning.<\/li>\n<\/ul>\n<p><strong>Session 8 \u2013 Mini Project: Deep Learning Case Study<\/strong><\/p>\n<ul>\n<li>Choosing dataset ( image,text and sound\/audio).<\/li>\n<li>Preprocessing and data exploration.<\/li>\n<li>Membangun model, pelatihan, dan evaluasi.<\/li>\n<li>Interpretasi hasil (visualisasi prediksi, confusion matrix).<\/li>\n<li>Mini project presentation.<\/li>\n<\/ul>\n<hr class=\"\" data-start=\"2710\" data-end=\"2713\" \/>\n<h3 class=\"\" data-start=\"2715\" data-end=\"2743\">\ud83c\udfaf <strong data-start=\"2722\" data-end=\"2743\">Learning Outcomes<\/strong><\/h3>\n<p class=\"\" data-start=\"2744\" data-end=\"2791\">By the end of this training, participants will:<\/p>\n<ul data-start=\"2792\" data-end=\"3002\">\n<li class=\"\" data-start=\"2792\" data-end=\"2861\">\n<p class=\"\" data-start=\"2794\" data-end=\"2861\">Understand the foundational concepts of Python for Deep Learning<\/p>\n<\/li>\n<li class=\"\" data-start=\"2862\" data-end=\"2907\">\n<p class=\"\" data-start=\"2864\" data-end=\"2907\">Use Python libraries for data science tasks<\/p>\n<\/li>\n<li data-start=\"2908\" data-end=\"2945\">\n<pre id=\"tw-target-text\" class=\"tw-data-text tw-text-large tw-ta\" dir=\"ltr\" role=\"text\" data-placeholder=\"Translation\" data-ved=\"2ahUKEwi7u967zdyQAxXvXGwGHVn2CaUQ3ewLegQIChAV\" aria-label=\"Translated text: Using Python and popular libraries (NumPy, Pandas, Matplotlib) to prepare the data.\"><span class=\"Y2IQFc\" lang=\"en\">Using Python and popular libraries (NumPy, Pandas, Matplotlib) to prepare the data.<\/span><\/pre>\n<\/li>\n<li class=\"\" data-start=\"2946\" data-end=\"3002\">\n<p class=\"\" data-start=\"2948\" data-end=\"3002\">Apply machine learning concepts to real-world projects<\/p>\n<\/li>\n<\/ul>\n<hr class=\"\" data-start=\"3004\" data-end=\"3007\" \/>\n<h3 class=\"\" data-start=\"3009\" data-end=\"3023\">\ud83d\udcde Contact<\/h3>\n<ul data-start=\"3024\" data-end=\"3182\">\n<li class=\"\" data-start=\"3024\" data-end=\"3089\">\n<p class=\"\" data-start=\"3026\" data-end=\"3089\">\ud83d\udce7 Email: <a class=\"cursor-pointer\" rel=\"noopener\" data-start=\"3036\" data-end=\"3087\">wbudiharto@binus.edu<\/a><\/p>\n<\/li>\n<li class=\"\" data-start=\"3090\" data-end=\"3136\">\n<p class=\"\" data-start=\"3092\" data-end=\"3136\">\ud83d\udcf1 Mr. Prof. Widodo (WhatsApp): +62 856 9887 384<\/p>\n<\/li>\n<li class=\"\" data-start=\"3137\" data-end=\"3182\">\n<p class=\"\" data-start=\"3139\" data-end=\"3182\">\ud83d\udcf1 Ms. Dr. Emny (WhatsApp): +62 813 8741 3863<\/p>\n<\/li>\n<\/ul>\n<hr \/>\n<h2 class=\"\" style=\"text-align: center\" data-start=\"162\" data-end=\"191\"><strong data-start=\"168\" data-end=\"189\">Silabus Pelatihan<\/strong><\/h2>\n<h3 class=\"\" style=\"text-align: center\" data-start=\"192\" data-end=\"237\">Python Programming for Deep Learning<\/h3>\n<h4 data-start=\"266\" data-end=\"280\">\ud83d\udd58 Durasi: <strong>4\u00a0hari fullday<\/strong> (08:00 &#8211; 17:00 WIB)<\/h4>\n<h4 data-start=\"321\" data-end=\"351\">\ud83d\udc65 Jumlah Peserta Minimum: <strong data-start=\"352\" data-end=\"363\">5 orang<\/strong><\/h4>\n<h4 data-start=\"365\" data-end=\"378\">\ud83d\udcbc Biaya: <strong data-start=\"379\" data-end=\"429\">Sesuai dengan kesepakatan dan lokasi pelatihan<\/strong><\/h4>\n<hr class=\"\" data-start=\"431\" data-end=\"434\" \/>\n<h3 class=\"\" data-start=\"436\" data-end=\"466\">\ud83d\udccb <strong data-start=\"443\" data-end=\"466\">Deskripsi Pelatihan<\/strong><\/h3>\n<p>Pelatihan <strong>Python Programming for Deep Learning<\/strong> ini dirancang untuk peserta yang telah memahami dasar-dasar Python dan ingin melangkah lebih jauh ke dunia <strong>kecerdasan buatan (AI)<\/strong>, khususnya <strong>deep learning<\/strong>. Peserta akan belajar bagaimana Python digunakan untuk membangun, melatih, dan mengevaluasi model neural network menggunakan pustaka modern seperti <strong>TensorFlow<\/strong> dan <strong>Keras<\/strong>.<\/p>\n<p>Pelatihan ini berfokus pada <strong>praktik langsung (hands-on coding)<\/strong> dan <strong>studi kasus nyata<\/strong>, agar peserta dapat memahami alur kerja deep learning dari preprocessing data, arsitektur model, pelatihan (training) hingga evaluasi.<\/p>\n<hr class=\"\" data-start=\"906\" data-end=\"909\" \/>\n<h3 class=\"\" data-start=\"911\" data-end=\"949\">\ud83d\udcda <strong data-start=\"918\" data-end=\"949\">Materi yang Akan Dipelajari<\/strong><\/h3>\n<p><strong>Sesi 1 \u2013 Pengenalan Deep Learning dan Environment<\/strong><\/p>\n<ul>\n<li>Review singkat Python dan NumPy<\/li>\n<li>Konsep Machine Learning vs Deep Learning<\/li>\n<li>Arsitektur Neural Network<\/li>\n<li>Instalasi dan setup TensorFlow\/Keras<\/li>\n<li>Hands-on<\/li>\n<\/ul>\n<p><strong>Sesi 2 \u2013 Persiapan dan Manipulasi Data untuk Deep Learning<\/strong><\/p>\n<ul>\n<li>Data loading dan preprocessing (normalisasi, one-hot encoding)<\/li>\n<li>Split data: training, validation, test<\/li>\n<li>Menggunakan Pandas dan scikit-learn untuk pipeline data<\/li>\n<li>Visualisasi distribusi data dengan Matplotlib\/Seaborn<\/li>\n<li>Hands-on: Dataset MNIST dan analisis awal<strong style=\"font-family: inherit\">\u00a0<\/strong><\/li>\n<\/ul>\n<p><strong>Sesi 3 \u2013 Membangun dan Melatih Neural Network<\/strong><\/p>\n<ul>\n<li>Konsep layer, neuron, activation function, loss, dan optimizer<\/li>\n<li>Backpropagation dan gradient descent (konsep intuitif)<\/li>\n<li>Implementasi model DNN (Fully Connected Network)<\/li>\n<li>Evaluasi model: accuracy, loss curve<\/li>\n<li>Hands-on: Membangun model klasifikasi digit (MNIST)<\/li>\n<\/ul>\n<p><strong>Sesi 4 \u2013 Convolutional Neural Network (CNN) untuk Data Gambar<\/strong><\/p>\n<ul>\n<li>Konsep convolution, pooling, dan filter<\/li>\n<li>Arsitektur CNN populer<\/li>\n<li>Implementasi CNN dengan Keras<\/li>\n<li>Augmentasi data untuk meningkatkan performa<\/li>\n<li>Hands-on: Klasifikasi gambar<\/li>\n<\/ul>\n<p><strong>Sesi 5 \u2013 Recurrent Neural Network (RNN) dan LSTM untuk Data Sequential<\/strong><\/p>\n<ul>\n<li>Konsep sequence data dan temporal dependencies<\/li>\n<li>Arsitektur RNN dan LSTM<\/li>\n<li>Implementasi RNN\/LSTM dengan Keras<\/li>\n<li>Studi kasus: Analisis sentimen teks sederhana<\/li>\n<li>Hands-on: Prediksi teks<\/li>\n<\/ul>\n<p><strong>Sesi 6 \u2013 Optimisasi dan Evaluasi Model<\/strong><\/p>\n<ul>\n<li>Overfitting vs underfitting<\/li>\n<li>Regularisasi (Dropout, Early Stopping)<\/li>\n<li>Hyperparameter tuning<\/li>\n<li>Model evaluation dan confusion matrix<\/li>\n<li>Hands-on: Meningkatkan performa model CNN<\/li>\n<\/ul>\n<p><strong>Sesi 7 \u2013 Transfer Learning dan Fine-Tuning<\/strong><\/p>\n<ul>\n<li>Konsep transfer learning<\/li>\n<li>Menggunakan model pre-trained (MobileNet, ResNet, EfficientNet)<\/li>\n<li>Fine-tuning untuk dataset kustom<\/li>\n<li>Hands-on: Klasifikasi gambar kustom dengan transfer learning<\/li>\n<\/ul>\n<p><strong>Sesi 8 \u2013 Mini Project: Deep Learning Case Study<\/strong><\/p>\n<ul>\n<li>Pemilihan dataset (gambar, teks, atau suara)<\/li>\n<li>Preprocessing dan eksplorasi data<\/li>\n<li>Membangun model, pelatihan, dan evaluasi<\/li>\n<li>Interpretasi hasil (visualisasi prediksi, confusion matrix)<\/li>\n<li>Presentasi hasil mini project<\/li>\n<\/ul>\n<hr class=\"\" data-start=\"1207\" data-end=\"1210\" \/>\n<h3 class=\"\" data-start=\"1212\" data-end=\"1239\">\ud83c\udfaf <strong data-start=\"1219\" data-end=\"1239\">Tujuan Pelatihan<\/strong><\/h3>\n<p>Setelah mengikuti pelatihan ini, peserta diharapkan mampu:<\/p>\n<ol>\n<li>Memahami konsep dasar <strong>machine learning<\/strong> dan <strong>deep learning.<\/strong><\/li>\n<li>Menggunakan <strong>Python dan library populer (NumPy, Pandas, Matplotlib)<\/strong> untuk menyiapkan data.<\/li>\n<li>Memahami struktur dasar <strong>neural network<\/strong> dan proses pelatihannya.\n<ol>\n<li style=\"list-style-type: none\"><\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<hr class=\"\" data-start=\"1513\" data-end=\"1516\" \/>\n<h3 class=\"\" data-start=\"1518\" data-end=\"1531\">\ud83d\udcde Kontak<\/h3>\n<ul data-start=\"1532\" data-end=\"1679\">\n<li class=\"\" data-start=\"1532\" data-end=\"1597\">\n<p class=\"\" data-start=\"1534\" data-end=\"1597\">\ud83d\udce7 Email: <a class=\"cursor-pointer\" rel=\"noopener\" data-start=\"1544\" data-end=\"1595\">wbudiharto@binus.edu<\/a><\/p>\n<\/li>\n<li class=\"\" data-start=\"1598\" data-end=\"1639\">\n<p class=\"\" data-start=\"1600\" data-end=\"1639\">\ud83d\udcf1 Bpk. Prof. Widodo (WA): +62 856 9887 384<\/p>\n<\/li>\n<li class=\"\" data-start=\"1640\" data-end=\"1679\">\n<p class=\"\" data-start=\"1642\" data-end=\"1679\">\ud83d\udcf1 Ibu Dr. Emny (WA): +62 813 8741 3863<\/p>\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Training Syllabus \ud83d\udd58 Duration: 4\u00a0full days (08:00 AM \u2013 04:00 PM GMT+7) \ud83d\udc65 Minimum Participants: 5 people \ud83d\udcbc Fee: Based on agreement and venue \ud83d\udccb Training Overview This Python Programming for Deep Learning training is designed for participants who already understand the basics of Python and want to delve deeper into the world of artificial [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":187,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[11],"tags":[],"class_list":["post-278","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-syllabus"],"_links":{"self":[{"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/posts\/278","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/comments?post=278"}],"version-history":[{"count":8,"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/posts\/278\/revisions"}],"predecessor-version":[{"id":395,"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/posts\/278\/revisions\/395"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/media\/187"}],"wp:attachment":[{"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/media?parent=278"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/categories?post=278"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/binus.ac.id\/humanitarian-ai\/wp-json\/wp\/v2\/tags?post=278"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}