Minimal character-level language model with a Vanilla Recurrent Neural Network, in Python/numpy

TensorFlow Variable-Length Sequence Labelling

This example demonstrates a TensorFlow recurrent neural network that labels variable-length sequences, using GRU cells to process input data and a softmax layer to classify each time step. It defines a `VariableSequenceLabelling` class with lazy properties for prediction, cost, and error, and relies on TensorFlow’s `dynamic_rnn`, `rnn_cell.GRUCell`, and Adam optimizer. The model is trained and evaluated on an OCR dataset from the `sets` library, reshaping flattened images and using one-hot encoded targets, with training and test splits provided by `sets.Split`.

MMissHanJ

57% match

using-pretrained-abstract-to-tweet-model.ipynb

This example shows how a pre-trained transformer model converts academic abstracts into concise, tweet-sized summaries, demonstrating a text-to-text generation workflow. It loads a Hugging Face `AutoModelForSeq2SeqLM` and `AutoTokenizer` from the `andersoncliffb/abstracts_to_tweet_model` repository, then creates a `text2text-generation` pipeline to produce the output. The notebook’s code uses the Transformers library’s pipeline API, with the model and tokenizer specified directly. It does not include a data visualization, instead focusing on the model’s generative output from input text.

CCliffordAnderson

52% match

Gist 504719be190c80e2cec9228ea8849c7f

This example shows a handwritten digit recognition system built in Processing. It displays a neural network with 196 input nodes, 49 hidden nodes, and 10 output nodes, trained on the MNIST dataset. The sketch loads a sigmoid activation function and constructs the network via the custom `Network` class. As the user draws on a canvas, the network classifies the input and visualizes the activations propagating through the layers. The code uses Processing’s `setup()` and `loadSigmoid()` methods to initialize the model and rendering.

49% match

Gist 36fa85de37aeb50756ec65aa6548b25f

This example implements an artificial neural network where individual neurons are drawn as circles on a canvas. Each neuron connects to a set of previous-layer inputs, multiplying their output values by random weights, then passing the summed result through a sigmoid activation function. The code renders each neuron’s fill color based on its output value, using the Processing API’s `ellipse()` and `fill()` functions to visualize activation levels. The neural activity propagates layer by layer, producing a dynamic, self-contained simulation of a feedforward network without external data inputs.

Gist 99f0384031106e9fdc7a0d325cd88606

This example demonstrates a neural network classifier for handwritten digits. A Processing sketch displays the network architecture, and mouse clicks either train the network on 500 random samples from the training set or respond to a single test sample. The code uses Processing's `loadPixels()` and `redraw()` functions, alongside custom `Network`, `loadData()`, and `setupSigmoid()` methods, to visualize the network’s layered connections in real time.

Gist d6e2a2307801a1a2d367875fe3cf671a

This example demonstrates a three-layer neural network learning to classify patterns through supervised backpropagation. The Processing sketch uses a custom `Neuron` class with a training loop that adjusts connection weights based on error signals. The code shows the core training mathematics, including a hyperbolic tangent activation function, delta computation, and weight updates scaled by a fixed learning rate. The visualization itself is not present in this code fragment, which focuses solely on the algorithmic update logic for each neuron’s error and weight adjustment.

Gist 232b1f382c6798335ff1f889303e9f62

This example visualizes a neural network’s response to input cards, showing how activation flows from the input layer through the hidden layer to the output layer. The code, written in Processing, defines a `Network` class whose `respond()` method assigns each card’s input values to the input layer’s neurons, then sequentially calls `respond()` on each hidden and output neuron to propagate signals. It uses the `Card` class for data inputs and the `Network`’s internal layer arrays to manage neurons, demonstrating a feedforward computation without any external visualization library.

Gist 628b2fab1b21dd2fd74ddc2e7469261f

This interactive visualization demonstrates a neural network classifying handwritten digits from the MNIST dataset, showing the network’s ten output activations for each input image. It uses Processing’s `loadBytes()` to read 196-byte image data and 10,000 label bytes, splitting the data set so that four out of five cards train the model while every fifth card tests it. The code defines a `Card` class that stores input arrays and output arrays, highlighting the correct answer within the template outputs during label loading.