Deep-learning - TechnoScripts

deep-learning

Deep learning tutorials in Python covering neural networks, training, and common frameworks.

DL: Optimizers, Why Your Model Learns (or Doesn’t)

Python optimizers are what turn a stack of layers into a model that actually learns, and Adam is the one almost everyone reaches for first, for good reason. This guide shows why Adam is the safe default, when plain SGD (Stochastic Gradient Descent) with momentum can still beat it, and how to choose between SGD, Momentum, RMSprop, Adam, and AdamW using real training runs instead of folklore. “Adam combines the advantages of AdaGrad and RMSProp into a single update rule.” ... Read More

DL: CNNs, Convolution, Pooling, Image Classification

Want to build a Python CNN that actually sees an image? This guide walks through convolution, pooling, feature maps, and the layer-by-layer feature extraction that makes CNNs the backbone of modern computer vision. By the end you train an image classifier on the MNIST handwritten digits from scratch, in PyTorch, and watch the accuracy climb to around 99 percent. “The first layer learns edges, the next learns textures, then parts, and the final layers learn whole objects. That step-by-step build ... Read More

DL: Transfer Learning with ResNet, VGG Pre-trained Models

Transfer learning lets you reuse a model that already learned to see, then point it at your own problem with a tiny dataset. This transfer learning Python guide shows feature extraction versus fine-tuning with ResNet, VGG, and EfficientNet, so you can classify custom images with far less data than training a network from scratch. “After supervised learning, transfer learning will be the next driver of ML commercial success.” Andrew Ng, NIPS 2016 tutorial Last Updated: July 2026 | Tested on: ... Read More