SentinelA new way to search

Search VoicesBlog

Sign In Sign Up

Sentinel keeps the record.

A permanent, searchable index of what is said in the video content shaping public conversation — built to support discovery and accountability across the voices that drive it.

Submit a Voice Request

Platform

Search
Browse Voices
Voices
Drive Again
Coverage
Custom Feed
Video Check
Statistics

Resources

Blog
Help
FAQ
Voice Request
Changelog
Sitemap

Company

About
Features
Pricing
Contact

Legal

Terms of Service
Privacy Policy
Acceptable Use
Cookies
Refund Policy
DMCA Policy

No content is hosted on Sentinel. All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel is an organization and analytics platform that provides research tools to promote discovery and accountability across the video content shaping public conversation. Views, credit, subscriptions, and engagement remain with the original channels.

© 2026 SentinelSearch. All rights reserved.

Indexing what Voices say, when they say it.

Sebastian Raschka · Sentinel

Sebastian Raschka

Sebastian Raschka

@sebastianraschka•88.6K subscribers•307 videos

Watch on YouTube Visit Website

About Sebastian Raschka

researcher

Watch

YouTube Official Website

Listen

Apple Podcasts RSS Feed

Follow

307

Videos

88.6K

Subscribers

3M

Total Views

Feb 21, 2012

Joined YouTube

Sebastian Raschka Episode Catalog

Explore every episode. Find what matters.

Build A Reasoning Model Scratch 2: Loading a Base Model, Text Generation, and KV Caching

6.2K1178

OpenAI Astra and Recurrent Depth / Looped Transformers

26.7K40142

Build A Reasoning Model Scratch 1: Motivation & Code Setup

11K26133

How Claude's Text Watermarking Works

1.2K7416

Build A Reasoning Model (From Scratch), Page 198

3542

What I Learned From Implementing LLM Architectures From Scratch (And How to Get Started)

23.3K1.1K66

A Visual Tour of Modern LLM Architectures

14.5K72548

LLM Building Blocks & Transformer Alternatives

19.1K66137

The Big LLM Architecture Comparison

41.6K1.7K60

Build an LLM from Scratch 7: Instruction Finetuning

43K75765

Build an LLM from Scratch 6: Finetuning for Classification

27K61139

Build an LLM from Scratch 5: Pretraining on Unlabeled Data

32.4K65436

Build an LLM from Scratch 4: Implementing a GPT model from Scratch To Generate Text

33.6K65740

Build an LLM from Scratch 3: Coding attention mechanisms

58.9K1.1K68

Build an LLM from Scratch 2: Working with text data

92K1.7K112

Build an LLM from Scratch 1: Set up your code environment

157K2.9K117

Reinforcement Learning with Human Feedback (RLHF) in 4 minutes

15.1K3146

LLMs: A Journey Through Time and Architecture

11.7K42050

Building LLMs from the Ground Up: A 3-hour Coding Workshop

166.5K5.1K166

Understanding PyTorch Buffers

11.7K41545

Developing an LLM: Building, Training, Finetuning

141.2K3.6K106

Developing and Training LLMs From Scratch with Sebastian Raschka

8.4K2511

Managing Sources of Randomness When Training Deep Neural Networks

3.2K10310

767: Open-Source LLM Libraries and Techniques — with Dr. Sebastian Raschka

3.7K1268

Insights from Finetuning LLMs with Low-Rank Adaptation

11.3K35620

Finetuning Open-Source LLMs

41.5K1K23

Scaling PyTorch Model Training With Minimal Code Changes

8K12913

Sebastian Raschka, University of Wisconsin-Madison/ Lead AI Education, Grid.AI

31260

Anaconda 10-Year Anniversary: Does Numerical Computing Have An Open Future?

947270

L13.5 What's The Difference Between Cross-Correlation And Convolution?

11.4K13911

Conditional Ordinal Regression for Neural Networks (CORN) With Examples in PyTorch

6.3K14518

Data Exchange Podcast (Episode 127): Sebastian Raschka

4.6K231

[53c] Q&A: Sebastian Raschka & Adrian Wälchli (PyTorch, LightningLite)

47484

[53b] Scaling Up with LightningLite (Adrian Wälchli)

452100

[53a] Intro to PyTorch Tutorial (Sebastian Raschka)

3.4K804

The Three Elements of PyTorch

8.7K31716

Making Machine Learning more accessible | Sebastian Raschka, Lead AI Educator, Grid.ai

1.4K395

Advancing Hands-On Machine Learning Education with Sebastian Raschka - #565

1.3K310

Ratings and Rankings -- Using Deep Learning When Class Labels Have A Natural Order

1.5K439

13.4.5 Sequential Feature Selection -- Code Examples (L13: Feature Selection)

13.9K22136

13.4.4 Sequential Feature Selection (L13: Feature Selection)

14.2K23434

13.4.3 Feature Permutation Importance Code Examples (L13: Feature Selection)

10.6K17613

13.4.2 Feature Permutation Importance (L13: Feature Selection)

16.2K35430

13.4.1 Recursive Feature Elimination (L13: Feature Selection)

14.9K24518

13.3.2 Decision Trees & Random Forest Feature Importance (L13: Feature Selection)

18K30320

13.3.1 L1-regularized Logistic Regression as Embedded Feature Selection (L13: Feature Selection)

6.5K995

AMA with Dr. Sebastian Raschka, Lead AI Educator at Grid.ai

1.3K420

13.2 Filter Methods for Feature Selection -- Variance Threshold (L13: Feature Selection)

7.9K1135

13.1 The Different Categories of Feature Selection (L13: Feature Selection)

6.9K1289

13.0 Introduction to Feature Selection (L13: Feature Selection)

6.6K14919

Introduction to Generative Adversarial Networks (Tutorial Recording at ISSDL 2021)

3.9K596

Designing Generative Adversarial Networks for Privacy-enhanced Face Recognition (Conference rec.)

742171

Transformers from the Ground Up - Sebastian Raschka | PyData Jeddah

9.9K2544

L19.5.2.2 GPT-v1: Generative Pre-Trained Transformer

11.7K1659

L19.5.2.4 GPT-v2: Language Models are Unsupervised Multitask Learners

5.3K830

L19.5.2.7: Closing Words -- The Recent Growth of Language Transformers

2.5K454

L19.5.2.6 BART: Combining Bidirectional and Auto-Regressive Transformers

6.1K894

L19.5.2.5 GPT-v3: Language Models are Few-Shot Learners

4.5K655

L19.6 DistilBert Movie Review Classifier in PyTorch -- Code Example

8.1K13719

L19.5.2.3 BERT: Bidirectional Encoder Representations from Transformers

9.7K1585

L19.5.2.1 Some Popular Transformer Models: BERT, GPT, and BART -- Overview

15K1927

L19.5.1 The Transformer Architecture

23.7K45724

L19.4.3 Multi-Head Attention

32.8K36428

L19.4.2 Self-Attention and Scaled Dot-Product Attention

24.9K45826

L19.4.1 Using Attention Without the RNN -- A Basic Form of Self-Attention

15.9K30328

L19.3 RNNs with an Attention Mechanism

22.3K35919

L19.2.1 Implementing a Character RNN in PyTorch (Concepts)

6.1K833

L19.2.2 Implementing a Character RNN in PyTorch --Code Example

6.9K728

L19.1 Sequence Generation with Word and Character RNNs

10.9K1509

L19.0 RNNs & Transformers for Sequence-to-Sequence Modeling -- Lecture Overview

8.1K991

L18.6: A DCGAN for Generating Face Images in PyTorch -- Code Example

9K12711

L18.5: Tips and Tricks to Make GANs Work

4.5K864

L18.4: A GAN for Generating Handwritten Digits in PyTorch -- Code Example

8.2K1237

L18.3: Modifying the GAN Loss Function for Practical Use

7.1K10715

L18.2: The GAN Objective

4.8K835

L18.1: The Main Idea Behind GANs

4.4K692

L18.0: Introduction to Generative Adversarial Networks -- Lecture Overview

4.1K551

L17.7 VAE Latent Space Arithmetic in PyTorch -- Making People Smile (Code Example)

7.5K1548

L17.6 A Variational Autoencoder for Face Images in PyTorch -- Code Example

7.8K919

L17.5 A Variational Autoencoder for Handwritten Digits in PyTorch -- Code Example

18.3K27519

L17.4 Variational Autoencoder Loss Function

12.5K20314

L17.3 The Log-Var Trick

8.3K1253

L17.2 Sampling from a Variational Autoencoder

12K19213

L17.1 Variational Autoencoder Overview

22.2K25412

L17.0 Intro to Variational Autoencoders -- Lecture Overview

5.5K787

L16.5 Other Types of Autoencoders

12.5K1374

L16.4 A Convolutional Autoencoder in PyTorch -- Code Example

15.3K23014

L16.3 Convolutional Autoencoders & Transposed Convolutions

19.9K41039

L16.2 A Fully-Connected Autoencoder

5.7K11910

L16.1 Dimensionality Reduction

6.7K974

L16.0 Introduction to Autoencoders -- Lecture Overview

6.6K876

L15.7 An RNN Sentiment Classifier in PyTorch

16.3K25729

L15.6 RNNs for Classification: A Many-to-One Word RNN

7.8K13418

L15.5 Long Short-Term Memory

9.7K18818

L15.4 Backpropagation Through Time Overview

47.3K66514

L15.3 Different Types of Sequence Modeling Tasks

4.9K594

L15.2 Sequence Modeling with RNNs

8.5K1012

L15.1: Different Methods for Working With Text Data

6.8K836

L15.0: Introduction to Recurrent Neural Networks -- Lecture Overview

5.4K735

L14.6.2 Transfer Learning in PyTorch -- Code Example

3.6K6610

L14.6.1 Transfer Learning

2.4K304

L14.5 Convolutional Instead of Fully Connected Layers

5.1K802

L14.4.2 All-Convolutional Network in PyTorch -- Code Example

2.2K280

L14.4.1 Replacing Max-Pooling with Convolutional Layers

3.2K451

Deep Learning News #10, Apr 3 2021

1.6K286

L14.3.2.2 ResNet-34 in PyTorch -- Code Example

12.6K16116

L14.3.2.1 ResNet Overview

4.5K5813

L14.3.1.2 VGG16 in PyTorch -- Code Example

11.8K16220

L14.3.1.1 VGG16 Overview

29K2911

L14.3: Architecture Overview

1.9K190

L14.2: Spatial Dropout and BatchNorm

3.5K420

L14.1: Convolutions and Padding

3.2K470

L14.0: Convolutional Neural Networks Architectures -- Lecture Overview

2.3K271

Deep Learning News #9, Mar 27 2021

1.6K439

L13.9.3 AlexNet in PyTorch

7.4K8613

L13.9.2 Saving and Loading Models in PyTorch

6.9K855

L13.9.1 LeNet-5 in PyTorch

6.1K5911

L13.8 What a CNN Can See

3.1K594

L13.7 CNN Architectures & AlexNet

4.2K574

L13.6 CNNs & Backpropagation

11.4K1305

Deep Learning News #8 Mar 20 2021

1.8K250

L13.5 Cross-correlation vs. Convolution (Old)

8.5K11511

L13.4 Convolutional Filters and Weight-Sharing

12.1K25524

L13.3 Convolutional Neural Network Basics

5.2K851

L13.2 Challenges of Image Classification

3.3K541

L13.1 Common Applications of CNNs

4.9K582

L13.0 Introduction to Convolutional Networks -- Lecture Overview

3.8K553

L12.6 Additional Topics and Research on Optimization Algorithms

1.9K321

L12.5 Choosing Different Optimizers in PyTorch

4.3K683

L12.4 Adam: Combining Adaptive Learning Rates and Momentum

8.1K1408

L12.3 SGD with Momentum

4.8K882

L12.2 Learning Rate Schedulers in PyTorch

3.6K657

L12.1 Learning Rate Decay

4.5K821

L12.0: Improving Gradient Descent-based Optimization -- Lecture Overview

2.4K371

Deep Learning News #7 Mar 13 2021

1.4K242

L11.7 Weight Initialization in PyTorch -- Code Example

4.1K692

L11.6 Xavier Glorot and Kaiming He Initialization

17.1K2418

L11.5 Weight Initialization -- Why Do We Care?

4.4K582

L11.4 Why BatchNorm Works

3.2K598

L11.3 BatchNorm in PyTorch -- Code Example

4.5K525

L11.2 How BatchNorm Works

5.9K999

L11.1 Input Normalization

4.3K671

L11.0 Input Normalization and Weight Initialization -- Lecture Overview

2.9K350

L10.5.4 Dropout in PyTorch

5.1K947

L10.5.3 (Optional) Dropout Ensemble Interpretation

2.5K413

L10.5.2 Dropout Co-Adaptation Interpretation

2.9K330

L10.5.1 The Main Concept Behind Dropout

3.9K494

L10.4 L2 Regularization for Neural Nets

6.5K964

L10.3 Early Stopping

9K796

L10.2 Data Augmentation in PyTorch

5.3K636

Showing 1–150 of 336

1/3