This is your work, valued

London

Rakeshvara R.A.

Elite
@rakeshvar

Stanford PhD in AI | 13+ years Deep Learning (Transformers & Diffusion). Currently building Penrose Diffusion models & Sanskrit LLMs. Open to frontier AI roles.

rnn_ctc. Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.

221

banti_telugu_ocr. End to end OCR system for Telugu. Based on Convolutional Neural Networks.

52

theanet. Convolutional Neural Network for Image Classification with Theano.

51

chamanti_ocr_theano. Telugu OCR framework using RNN, CTC in Theano & Python3.

46

Zygote-Mutating-Arrays-WorkAround.jl. A tutorial on how to work around ‘Mutating arrays is not supported’ error while performing automatic differentiation (AD) using the Julia package Zygote.

30

stacked_denoising_auto_encoder. Stacked Denoising Auto-Encoder in Theano. Using the mnist dataset.

14

AnyBoost.jl. A julia based machine learning package for boosting any loss, activation and constraint.

10

kmedoids. K-medoids unsupervised clustering. Implemented in Python and Numpy. Vectorized to work for huge datasets.

8

code_in_telugu. తెలుఁగులో యంత్రలిపి వ్రాయుట ఎలా

7

unicode_text_to_image_array. Converts a piece of complex unicode text to an image and a numpy arrray.

7

cifar. State-of-the-art results in Cifar 100 using theano and theanet. Convolutional Neural Networks with Data Augmentation.

6

neural-sanskrit. A Neural Network that learns to predict Sanskrit text and learns vector representations for the Aksharas(syllables).

5

banti_training. Datasets to train Telugu OCR using theanet.

3

cowboxer. Automatically exported from code.google.com/p/cowboxer

2

TeluguCorpus. Some ngram models on the Telugu Corpus

1

telugu_fonts. Comprehensive list of free Telugu Fonts.

1

theano-hf. General purpose Hessian-free optimization in Theano

1

SanskritGPT. Training a Generatively Pre-trained Transformer on Sanskrit data.

1

penrose_diffusion. Permutation Invariant DDPM/DDIM Model on Sets} to sample-without-repetition chaotic aperiodic tilings on zero-measure fractal manifolds. Built a plug-and-play architecture for Transformer Denoisers, VAE Latent Space Learning, Discrete Diffusers and LLM style Auto-regressive GPTs. Probes the limits of class-conditioned structure discovery.

1