Welcome to my TensorTonic solutions repository!
Here you'll find my solutions to various machine learning and deep learning problems from TensorTonic.
TensorTonic is a platform where you can implement core algorithms of Machine Learning from scratch.
This repository contains my personal solutions to these problems, automatically synchronized from the platform.
Verified machine learning implementations completed on TensorTonic.
| Problem | Description | Link |
|---|---|---|
| Implement Gradient Descent for a 1D Quadratic | Optimize a one-dimensional quadratic with iterative gradient descent and return the parameter trajectory. | https://www.tensortonic.com/problems/gradient-descent-quadratic |
| Matrix Transpose | Implement matrix transpose in NumPy without built-in transpose helpers, preserving rectangular shapes and the original input. | https://www.tensortonic.com/problems/matrix-transpose |
| Implement Sigmoid in NumPy | Implement a vectorized sigmoid activation in NumPy for scalars, lists, vectors, and matrices, including large positive and negative inputs. | https://www.tensortonic.com/problems/sigmoid-numpy |
| AlexNet Convolution Layer | Implement an AlexNet convolutional layer with learned filters, bias, stride, padding, and multi-channel outputs. | https://www.tensortonic.com/research/alexnet/alexnet-conv-layers |
| ReLU Activation Function | Implement AlexNet's elementwise ReLU activation, preserving positive values while setting negative values to zero. | https://www.tensortonic.com/research/alexnet/alexnet-relu |
| Convolutional Block | Implement a ResNet convolutional block with a projected shortcut that matches changed spatial and channel dimensions. | https://www.tensortonic.com/research/resnet/resnet-conv-block |
| Identity Block | Implement a ResNet identity block with a three-layer bottleneck branch, batch normalization, ReLU, and an unchanged skip path. | https://www.tensortonic.com/research/resnet/resnet-identity-block |
| Embedding Layer | Create PyTorch token embeddings and scale each lookup by the square root of the Transformer model dimension. | https://www.tensortonic.com/research/transformer/transformers-embedding |
| Tokenization | Build a word-level Transformer tokenizer with fixed special-token IDs, sorted vocabulary entries, encoding, and decoding. | https://www.tensortonic.com/research/transformer/transformers-tokenization |
View my verified ML profile: TensorTonic profile