LMS-SPADA INDONESIA
Beranda
More
Login/Register
LMS-SPADA INDONESIA
Bahasa Indonesia (id)
Bahasa Indonesia (id)
English (en)
Login
×
Login to your account
Ingat username
Lupa kata sandi?
Masuk
Pencarian global tidak diaktifkan.
DEEP LEARNING
Beranda
Kursus
MATEMATIKA DAN ILMU PENGETAHUAN ALAM (MIPA)
MATEMATIKA
Ilmu Komputer
14624533 - DEEP LEARNING
10. Practical Methodology
Rubrik Penilaian Penugasan 9
Lewati ke konten utama
Berkas
Rubrik Penilaian Penugasan 9
Kriteria dan Bobot Penilaian :
Definisi Permasalahan (30%)
Tujuan Proyek (20%)
Observasi Pendekatan-Pendekatan Deep Learning (25%)
Instrumen Pengukuran Keberhasilan(10%)
Anti-plagiasi (15%)
Klik tautan
Rubrik Penilaian Penugasan 9 - Proposal Proyek Akhir.pdf
untuk melihat berkas.
◄ Materi 10: Practical Methodology
Lompat ke...
Lompat ke...
Pengumuman
Rencana Pembelajaran Semester (RPS)
Komposisi Penilaian & Evaluasi
Pengumuman
Rencana Pembelajaran Semester (RPS)
Komposisi Penilaian & Evaluasi
Diskusi Konsep Dasar Deep Learning
1.1. Deep Learning Application 2025_1
1.2. Hubungan AI & Deep Learning 2025_1
1.3. Why Deep Learning 2025_1
Materi 1: Konsep Dasar Deep Learning 2025_1
Penugasan 1: Meringkas literatur Deep Learning
Rubrik Penilaian Penugasan 1
Diskusi Konsep Dasar Deep Learning
Diskusi Matematika Untuk Mesin Pemelajar
2.1.1. Perkalian Matriks & Vektor
2.1.2. Determinan
2.1.3. Nilai Eigen dan Vektor Eigen
Materi 2.1. Math For ML - Aljabar Linier
2.2.1. Random Variable
2.2.2. Probability Mass Function (PMF)
2.2.3. Statistika Marginal
2.2.4.Probability Density Function
2.2.5. Statistika Variansi dan Kovariansi
2.2.6. Gaussian Distribution
Materi 2.2. Math for ML - Probabilitas
2.3.1. Gradient Based Optimization
2.3.2.Jacobian Matrices
2.3.3. Hessian Matrices
Materi 2.3. Math For ML - Komputasi Numerik
2.4. Dasar Mesin Pemelajar
Materi 2.4. Dasar Mesin Pemelajar
Penugasan 2: Identifikasi permasalahan matematika dan machine learning 2025_1
Rubrik Penilaian Penugasan 2
Diskusi Matematika Untuk Mesin Pemelajar 2025_1
3.1. Feedforward Neural Network
3.2. Backpropagation Algorithm
3.3. Minibatch
3.4. XOR Learning
Materi 3 : Deep Feedforward Networks
Rubrik Penilaian Penugasan 3
Diskusi Deep Feedforward Networks
4.1. Data Splitting
4.2. Problem of Fitting
4.3. Parameter Norm Penalties
4.4. Data Augmentation
4.5. Early Stopping
4.6. Bagging
4.7. Dropout
Materi 4: Regularization For Deep Learning
Rubrik Penilaian Penugasan 4
Diskusi Regularization For Deep Learning
5.1. NN as Computational Graph
5.2. Gradient Descent for NN
5.3. Optimization Algorithm
Materi 5: Optimization for Deep Learning
Rubrik penilaian penugasan 5
Diskusi Optimization for Deep Learning
6.1. Aplikasi Visi Komputer
6.2. Apa yang komputer lihat
6.3. Mempelajari Fitur Visual melalui Jaringan Saraf
6.4.Feature Extraction Case Study
6.5.Convolutional Neural Network (CNN)
6.6. Non Linearity & Pooling
6.7. Arsitektur Berbagai Aplikasi
Materi 6: Deep Convolutional Networks
Rubrik Penilaian Penugasan 6
Diskusi Deep Convolutional Networks
7.1. Introduction to Sequence Modelling
Materi 7: Deep Sequence Modelling
Rubrik Penugasan 7: Deep Sequence Modelling
Forum Diskusi 7 Deep Sequence Modelling
9.1. Autoregressive Models
Materi 8: Deep Generative Modeling
Penugasan 8: Deep Generative Modeling
Rubrik Penilaian Penugasan 8
Diskusi Deep Generative Modeling
10. Practical Methodology - Konsep
Materi 10: Practical Methodology
Kode Program 10-Practical Methodology
Forum Practical Methodology
Forum Diskusi Implementasi Deep Feedforward
11. Application Deep Feedforward Network in TensorFlow
Kode Program Deep Feedforward
Rubrik Penilaian Penugasan 10
Kode Program Telaah Data Terstruktur
Kode Program Visualisasi Data Terstruktur
Forum Diskusi Implementasi Deep Feedforward
12. Application Convolutional Neural Network in Tensor Flow
Kode Program Convolutional Neural Network
Rubrik Penilaian Tugas 11
Forum Diskusi Implementasi Convolutional Neural Network
13. Application Recurrent Neural Network (RNN) in Tensor Flow
Kode Program Recurrent Neural Network
Rubrik Penilaian Tugas 12
Forum Diskusi Application RNN
14. Application Deep Convolution Generative Adversarial Network (DC-GAN) in Tensor Flow
Kode Program Deep Convolutional Generative Adversarial Network
Rubrik Penilaian Tugas 13
Forum Diskusi Implementasi GAN
Kode Program 10-Practical Methodology ►
LMS-SPADA INDONESIA
Copyright © 2025 Spada Indonesia. All Rights Reserved.