Stochastic Gradient Descent Courses and Certifications

Erwin Schrödinger International Institute for Mathematics and Physics (ESI)

The Long-Run Distribution of Stochastic Gradient Descent: A Large Deviations Approach

Explore the long-run behavior of stochastic gradient descent in non-convex problems, analyzing state space visitation patterns and energy level distributions.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Erwin Schrödinger International Institute for Mathematics and Physics (ESI)

The First Optimal Distributed SGD in the Presence of Data, Compute and Communication Heterogeneity

Explore optimal time complexities for parallel optimization methods with heterogeneous data, compute, and communication. Gain insights into efficient distributed SGD algorithms.

• YouTube
• 29 minutes
• On-Demand
• Free Video

Erwin Schrödinger International Institute for Mathematics and Physics (ESI)

Hessian-Aware Stochastic Differential Equation Modeling of SGD

Explore a novel SDE model for SGD that incorporates Hessian information, improving accuracy in capturing escaping behaviors and achieving exact recovery for quadratic objectives.

• YouTube
• 29 minutes
• On-Demand
• Free Video

VinAI

Stochastic Gradient Descent Methods with Biased Estimators

Explore recent advancements in stochastic gradient descent methods, focusing on biased estimators for large-scale optimization and minimax problems in machine learning applications.

• YouTube
• 1 hour 7 minutes
• On-Demand
• Free Video

Stanford Seminar - Deep Learning in Speech Recognition

Explore deep learning's evolution and impact on speech recognition, from early AI to modern applications like Siri, covering key concepts, historical milestones, and practical implementations.

• YouTube
• 1 hour 13 minutes
• On-Demand
• Free Online Course

Information Theory of Deep Learning - Naftali Tishby

Explores the connection between deep learning and information theory, offering new insights into neural network design, generalization, and optimization through an information bottleneck framework.

• YouTube
• 1 hour 25 minutes
• On-Demand
• Free Video

Deep Learning Essentials

Explore neural networks, perceptrons, and deep learning fundamentals. Master backpropagation, stochastic gradient descent, and kernel methods through Python coding assignments.

• Coursera
• 15 hours 41 minutes
• On-Demand
• Free Online Course (Audit)

Neural Networks Made Easy

33 ratings at Udemy

Comprehensive introduction to neural networks, covering fundamentals, perceptrons, and coding from scratch. Includes hands-on challenges and focuses on deep understanding without relying on libraries.

• Udemy
• 1-2 hours
• On-Demand
• Free Online Course

Packt

Foundations of Deep Learning and Neural Networks

Master deep learning fundamentals, from neural network basics to advanced CNNs. Explore backpropagation, regularization techniques, and practical applications using TensorFlow and Keras. Ideal for tech professionals and students.

• Coursera
• 14 hours 4 minutes
• On-Demand
• Free Online Course (Audit)

Intro to Deep Learning

3 reviews

Use TensorFlow and Keras to build and train neural networks for structured data.

• Kaggle
• 4 hours
• On-Demand
• Free Certificate

Training Neural Networks for Computer Vision - Part I - Lecture 10

Explore neural network training techniques, including gradient descent, loss functions, and backpropagation, for effective computer vision model optimization and performance improvement.

• YouTube
• 36 minutes
• On-Demand
• Free Video

CAP5415 - Training Neural Networks Part 2 - Fall 2020 - Lecture 7

Explore advanced neural network training techniques, including loss functions, backpropagation, gradient descent optimization, and strategies to address common challenges in deep learning.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Building Classification Models with scikit-learn

48 ratings at Pluralsight

Learn to implement and evaluate various classification algorithms in scikit-learn, from logistic regression to advanced techniques like Support Vector Machines and Stochastic Gradient Descent.

• Pluralsight
• 2-3 hours
• On-Demand
• Free Trial Available

Gradient Descent: Building Optimization Algorithms from Scratch

Master optimization algorithms by implementing Gradient Descent variants from scratch, including Stochastic, Mini-Batch, Momentum, RMSProp, and Adam methods, with hands-on Python implementation and practical applications.

• CodeSignal
• On-Demand
• Paid Course

Centre for Networked Intelligence, IISc

Heterogeneity-Aware Algorithms for Federated Learning and Distributed Optimization

Delve into advanced federated learning algorithms, focusing on heterogeneity challenges in distributed model training and innovative solutions for edge computing optimization.

• YouTube
• 1 hour 8 minutes
• On-Demand
• Free Video