Meaningful Signals Within Deep Learning Models for Biology - Primer and Meeting
Explore deep learning models in biology, from curating meaningful pre-training data to disentangling experimental noise, enhancing performance in biomedical imaging and high-throughput microscopy experiments.
Batch Normalization
Explore batch normalization in deep learning: its implementation, benefits, and impact on network performance. Learn when and how to use it effectively for improved model training.
Convolution in Two Dimensions
Explore 2D convolution, softmax, and batch normalization. Build a CNN for MNIST digits using Cottonwood, covering model architecture, training, and evaluation techniques.
How Neural Networks Work
This video sequence tracks the lecture sequence in course 313 from the End to End Machine Learning School, How Neural Networks Work.
An Overview of Deep Learning and Neural Networks
Comprehensive introduction to deep learning concepts, covering neural networks, convolution, pooling, normalization, and more. Includes code examples for practical implementation.
Eigenvalue Distribution for Non Linear Models of Random Matrices
Explore eigenvalue distribution in non-linear random matrix models, covering motivation, limits, batch normalization, and moment methods with speaker Sandrine PECHE.
Deep Learning: Dropout and Batch Normalization - Lecture 5
Delve into dropout and batch normalization techniques, understanding their mechanisms and effectiveness in deep learning, with insights on loss function smoothness and Lipschitzness.
Building Makemore - Building a WaveNet
Dive deep into building a WaveNet-like convolutional neural network, exploring torch.nn, and understanding the typical deep learning development process through hands-on implementation.
Building Makemore - Becoming a Backprop Ninja
Hands-on tutorial on manual backpropagation through a 2-layer MLP, enhancing understanding of gradient flow in neural networks for confident innovation and debugging.
Building Makemore - Activations & Gradients, BatchNorm
Explore MLP internals, activations, gradients, and BatchNorm. Learn to diagnose deep networks, understand training challenges, and implement modern techniques for improved performance.
NFNets - High-Performance Large-Scale Image Recognition Without Normalization
Explore Normalizer-Free Networks, a novel approach to image recognition that achieves state-of-the-art accuracy without batch normalization, offering faster training and improved transfer learning performance.
NVAE- A Deep Hierarchical Variational Autoencoder
Detailed explanation of NVAE, a deep hierarchical variational autoencoder for high-resolution image generation, covering architecture, training techniques, and state-of-the-art results.
Batch Normalization in PyTorch - Adding Normalization to Convolutional Neural Network Layers
Learn to implement batch normalization in convolutional neural networks using PyTorch. Explore the benefits, create and compare networks, and optimize performance through hands-on coding and practical examples.
Group Normalization - Paper Explained
Explore Group Normalization as an alternative to Batch Normalization, addressing batch size limitations and improving performance in various deep learning tasks.
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Explore how Batch Normalization accelerates deep network training by reducing internal covariate shift, enabling higher learning rates and improved model performance.
Training Neural Networks and Deep Learning Optimization Methods - Lecture 16
Master neural network training fundamentals, from momentum methods and regularization to batch normalization, with practical applications in BBB transmission prediction and model optimization.