Deep learning
Neural networks from the ground up: layers, optimisers, CNNs, RNNs, GANs and training tricks.
Page 6 of 10
- Step-by-Step Diffusion Models and Flow Matching in Python6 min
Diffusion models are a class of generative models that learn to gradually denoise data. They start with pure noise and iteratively refine it into a desired...
- Surprising Vulnerability of Neural Networks to One-Pixel Attacks9 min
Neural networks are surprisingly vulnerable to minimal perturbations in input images. One-pixel attacks represent a fascinating subset of adversarial attacks...
- Building a Gradient Descent Optimizer from Scratch in Python6 min
Gradient descent is a fundamental optimization algorithm in machine learning. It's used to minimize a cost function by iteratively moving in the direction of...
- Enhancing Predictive Performance with Fibonacci Neural Networks and XGBoost10 min
Fibonacci Neural Networks and XGBoost Stacking are advanced techniques in machine learning that can significantly enhance predictive performance. This...
- Gradient Boosting Overfitting and Learning Rate5 min
Early stopping prevents overfitting by monitoring validation performance and stopping training when the model's performance starts to degrade, effectively...
- Recommender Systems Evaluation Metrics and Loss Functions in Python9 min
Recommender systems are algorithms designed to suggest relevant items to users based on their preferences and behavior. These systems are widely used in...
- The Importance of Data in Deep Learning18 min
Data quality assessment is fundamental in deep learning pipelines. This implementation demonstrates how to evaluate dataset characteristics including missing...
- Automatic Pruning of Kolmogorov-Arnold Networks11 min
Kolmogorov-Arnold Networks (KANs) are a type of neural network architecture inspired by the Kolmogorov-Arnold representation theorem. Automatic pruning in...
- Building a Neural Network for MNIST Dataset10 min
In this presentation, we'll explore the process of creating a neural network from the ground up and applying it to the MNIST dataset. We'll cover data...
- Building Simple Neural Networks with TensorFlow6 min
TensorFlow is a powerful open-source library for machine learning and deep learning. This slideshow will guide you through the process of creating basic...
- Calculus and Optimization in Neural Networks8 min
The foundation of neural networks rests on calculus principles, particularly in optimization during training. Understanding these mathematical concepts is...
- Calculus Foundations of Neural Networks9 min
Gradient descent forms the mathematical foundation of neural network training. It uses calculus to iteratively adjust network parameters by computing partial...
- Comparing KAN and MLP Neural Networks with Python13 min
KAN (Knowledge Augmented Network) and MLP (Multi-Layer Perceptron) are both neural network architectures used in machine learning. While MLPs have been...
- Comparing Kolmogorov Arnold Networks (KAN) and Multi-Layer Perceptron (MLP) in Python10 min
Kolmogorov Arnold Networks (KAN) and Multi-Layer Perceptron (MLP) are two different approaches to neural networks. KAN is based on the Kolmogorov-Arnold...
- Deep Learning and TensorFlow13 min
Deep Learning is a subset of Machine Learning that uses neural networks with multiple layers to learn from data. It has revolutionized various fields...
- Deep Learning Slideshow with TensorFlow and PyTorch11 min
Deep Learning is a subset of machine learning that uses artificial neural networks with multiple layers to learn and make decisions. It's inspired by the...
- Deep Learning Titans TensorFlow vs. PyTorch in Python9 min
TensorFlow and PyTorch are two of the most popular deep learning frameworks in the world of artificial intelligence and machine learning. Both offer powerful...
- Explaining Self-Attention and Masked Self-Attention in Deep Learning10 min
Attention mechanisms have revolutionized deep learning, particularly in sequence-to-sequence tasks and natural language processing. They allow models to...
- Introducing KAN 2.0! Kolmogorov-Arnold Networks in Python11 min
KAN 2.0, or Kolmogorov-Arnold Networks, represent an innovative approach to machine learning that combines principles from dynamical systems theory and...
- Introduction to Topological Deep Learning in Python13 min
Topological Deep Learning is an emerging field that combines concepts from topology, a branch of mathematics dealing with the study of shapes and spaces...
- Mastering Deep Learning Codebases for Beginners11 min
Deep learning codebases require systematic analysis starting with the research paper itself. The first step involves extracting key architectural decisions...
- Mastering Deep Learning with PyTorch12 min
PyTorch's fundamental building block is the tensor, a multi-dimensional array optimized for deep learning computations. Understanding tensor operations...
- Memory-Efficient Caching for Deep Learning with Python's Weakref9 min
Weak references allow objects to be garbage collected even when referenced by other objects, providing a powerful mechanism for memory management in...
- PyTorch DataLoader Efficient Data Handling for Deep Learning10 min
The PyTorch DataLoader is a powerful utility for efficiently loading and batching data in deep learning applications. It provides an iterable over a dataset...
- PyTorch for Deep Learning Practical Code Examples6 min
PyTorch has emerged as a leading framework for deep learning research and production, offering dynamic computational graphs, native Python integration, and...
- PyTorch Tutorial Building Neural Networks with Python5 min
PyTorch is an open-source machine learning library developed by Facebook's AI Research lab. It provides a flexible and efficient framework for building and...
- Self-Attention vs. Cross-Attention in Deep Learning9 min
Self-attention allows tokens in a sequence to weigh the importance of other tokens when encoding meaning. This fundamental mechanism enables models to...
- Time Series Forecasting! KAN vs. MLP in Python9 min
Time series forecasting is a crucial technique in data science for predicting future values based on historical data. This presentation will explore two...
- Tropical Algebraic Kolmogorov-Arnold Network! Improving KAN Neural Networks with Python10 min
Tropical Algebraic Kolmogorov-Arnold Networks (TAKANs) are a novel approach to improving Kolmogorov-Arnold Network (KAN) neural networks. They combine...
- Understanding Attention Layers in Neural Networks11 min
Attention layers are a crucial component of modern neural network architectures, particularly in natural language processing and computer vision tasks. They...