Loss Functions Courses and Certifications

Yannic Kilcher

Supervised Contrastive Learning

Explore a novel supervised learning approach that outperforms cross-entropy loss, improving image classification models' performance and robustness across various architectures and data augmentations.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Alfredo Canziani

CNN Loss

Explore convolutional neural network loss functions, including mean square error, cross-entropy, and negative log likelihood, with practical examples and implementation insights.

• YouTube
• 42 minutes
• Self-Paced
• Free Video

Custom Models, Layers, and Loss Functions with TensorFlow

1108 ratings at Coursera

Explore advanced TensorFlow techniques for building custom models, layers, and loss functions. Learn to create Siamese networks, implement contrastive loss, and extend the TensorFlow Model class to build a ResNet.

• Coursera
• 1 day 6 hours 57 minutes
• Self-Paced
• Paid Course

Alfredo Canziani

PyTorch Activation and Loss Functions

Explore activation and loss functions in PyTorch, including kink vs. smooth activations, margin-based losses, and designing effective loss functions for Energy-Based Models (EBMs).

• YouTube
• 1 hour 54 minutes
• Self-Paced
• Free Video

Introduction to Deep Learning with PyTorch

43 ratings at DataCamp

Learn how to build your first neural network, adjust hyperparameters, and tackle classification and regression problems in PyTorch.

• DataCamp
• 4 hours
• Self-Paced
• Free Trial Available

Linear Classifiers in Python

32 ratings at DataCamp

In this course you will learn the details of linear classifiers like logistic regression and SVM.

• DataCamp
• 4 hours
• Self-Paced
• Free Trial Available

UofU Data Science

Linear Classification and Loss Functions - Lecture 25

Dive into linear classifiers and loss functions, mastering fundamental concepts for effective data classification and model optimization techniques.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Introduction to Neural Networks with TensorFlow

Master neural networks and deep learning fundamentals using TensorFlow, from data preprocessing to model training. Build and optimize architectures, implement activation functions, and enhance model performance with the Digits dataset.

• CodeSignal
• 3 hours
• Self-Paced
• Free Certificate

Foundations of Optimization Algorithms

Master optimization algorithms from Newton's Method to adaptive learning rates, covering gradient descent, momentum techniques, and Adagrad for effective machine learning model tuning.

• CodeSignal
• 2 hours
• Self-Paced
• Free Certificate

Training Neural Networks: the Backpropagation Algorithm

Master backpropagation algorithm fundamentals through hands-on implementation of loss functions, gradient descent mechanics, and weight optimization for effective neural network training.

• CodeSignal
• 3 hours
• Self-Paced
• Free Certificate

Building and Applying Your Neural Network Library

Master neural network library development by refactoring code into reusable Python packages and applying them to real-world regression tasks like California Housing prediction.

• CodeSignal
• 2 hours
• Self-Paced
• Free Certificate

JAX in Action: Neural Networks from Scratch

Master neural network fundamentals by building an MLP from scratch using JAX, tackling XOR classification with parameter management, forward propagation, and manual training loops.

• CodeSignal
• 2 hours
• Self-Paced
• Free Certificate

Training Neural Networks: the Backpropagation Algorithm

Master backpropagation and gradient descent to train neural networks effectively through hands-on implementation of loss functions, optimizers, and complete training loops.

• CodeSignal
• 3 hours
• Self-Paced
• Free Certificate

Training Neural Networks: the Backpropagation Algorithm

Master the backpropagation algorithm by implementing loss functions, gradient descent, and SGD optimizers to train neural networks using R.

• CodeSignal
• 3 hours
• Self-Paced
• Free Certificate

Introduction to Neural Networks and Deep Learning with Python

Explore neural networks and deep learning with Python, covering optimization, regularization, transfer learning, and autoencoders to build, train, and evaluate models for real-world AI applications.

• edX
• 32 hours
• Self-Paced
• Free Online Course (Audit)