Chad Giusti - Topology, Convexity, and Neural Networks
Explore topology in neuroscience, focusing on receptive fields, neuron convexity, and geometric features. Discover connections between neural networks and mathematical concepts.
Feedforward and Feedback Processes in Visual Recognition
Explore visual recognition processes, comparing deep learning models with neuroscience-inspired approaches. Gain insights into complex visual reasoning and potential advancements in AI through computational neuroscience.
Deep Learning: Feedforward Neural Networks and Backpropagation - Lecture 2
Dive into fundamental concepts of deep learning, exploring perceptrons, feedforward neural networks, and mastering backpropagation techniques for neural network training.
Neural Networks Foundations - Feedforward Neural Networks
Master the fundamentals of feedforward neural networks, exploring their architecture, functionality, and implementation principles for building effective machine learning models.
Introduction to Neural Networks: Classification, Softmax, and Training Techniques
Master the fundamentals of neural networks, from nonlinear and multiclass classification to feedforward networks, training techniques, and optimization strategies for improved model performance.
CMU Multilingual NLP 2020 - Text Classification and Sequence Labeling
Explore text classification and sequence labeling in multilingual NLP, covering models, datasets, and neural networks for various language processing tasks.
Connections Between Physics and Deep Learning
Explore the fascinating intersections of physics and deep learning, from neural networks to scale-invariant behavior, with insights from MIT's Max Tegmark.
Composing Bach Chorales Using Deep Learning
Explore how deep learning and LSTM can compose Bach-style chorales, with insights from a musical Turing test revealing AI's potential for musical creativity.
The Narrated Transformer Language Model
Visual introduction to the Transformer architecture, explaining its components and applications in AI/ML. Accessible to various experience levels, covering tokenization, embedding, and output projection.