Akansha Saxena

One finds the best way to learn something new is to teach others.

Build an Agentic System using CrewAI | Hands on Tutorial
Build an Agentic System using CrewAI | Hands on Tutorial
Build an AI Automation Workflow using n8n
Build an AI Automation Workflow using n8n
Image Similarity App Codebase Explained
Image Similarity App Codebase Explained
Building a Mini Image Similarity Search Using CLIP and FAISS | Demo
Building a Mini Image Similarity Search Using CLIP and FAISS | Demo
What’s Next in AI/ML? My 4-Month Advanced Learning Challenge
What’s Next in AI/ML? My 4-Month Advanced Learning Challenge
Day 30: SimCLR self-supervised learning Part 2
Day 30: SimCLR self-supervised learning Part 2
Day 29: SimCLR Self-Supervised Learning - Part 1: Data Preparation & Architecture
Day 29: SimCLR Self-Supervised Learning - Part 1: Data Preparation & Architecture
Day 28: Fine-tune the BERT model on a custom NLP task
Day 28: Fine-tune the BERT model on a custom NLP task
Day 27: Build a simple transformer-based model (BERT) for text classification (IMDb Dataset)
Day 27: Build a simple transformer-based model (BERT) for text classification (IMDb Dataset)
Day 26: Train the CycleGAN on a smaller image set (like horse2zebra)
Day 26: Train the CycleGAN on a smaller image set (like horse2zebra)
Day 25: Implement CycleGAN for style transfer (e.g., horse to zebra conversion)
Day 25: Implement CycleGAN for style transfer (e.g., horse to zebra conversion)
Day 24: Build a Conditional GAN (CGAN) for generating specific images (Fashion MNIST)
Day 24: Build a Conditional GAN (CGAN) for generating specific images (Fashion MNIST)
Day 23: GAN Improvements - Enhancing Performance for Fashion MNIST Generation
Day 23: GAN Improvements - Enhancing Performance for Fashion MNIST Generation
Day 22: GAN Basics - Understanding GAN Architecture and Setting Up a GAN Framework
Day 22: GAN Basics - Understanding GAN Architecture and Setting Up a GAN Framework
Day 21: Fine-tune and evaluate autoencoder model for anomaly detection
Day 21: Fine-tune and evaluate autoencoder model for anomaly detection
Day 20: Build an autoencoder-based anomaly detection system (part 1: data and model setup)
Day 20: Build an autoencoder-based anomaly detection system (part 1: data and model setup)
Day 19: Attention Mechanism for LSTM in Machine Translation
Day 19: Attention Mechanism for LSTM in Machine Translation
Day 18 | Understanding Attention Mechanism for LSTM in Machine Translation
Day 18 | Understanding Attention Mechanism for LSTM in Machine Translation
Day 17 | Build an LSTM model for sentiment analysis (IMDb Dataset)
Day 17 | Build an LSTM model for sentiment analysis (IMDb Dataset)
Day 16 | Build a basic RNN model for sequence prediction (temperature forecasting)
Day 16 | Build a basic RNN model for sequence prediction (temperature forecasting)
Day 12 | Implement YOLO for object detection (tutorial-based approach to simplify)
Day 12 | Implement YOLO for object detection (tutorial-based approach to simplify)
Day 11 | Apply Transfer Learning with VGG16 for a simple classification task
Day 11 | Apply Transfer Learning with VGG16 for a simple classification task
Day 15 | Prepare a simple time series dataset (Jena Climate or stock data) for RNN model
Day 15 | Prepare a simple time series dataset (Jena Climate or stock data) for RNN model
Day 14 | Knowledge Distillation: Build a Custom CNN-based Model Using a Pre-Trained Model
Day 14 | Knowledge Distillation: Build a Custom CNN-based Model Using a Pre-Trained Model
Day 13 Part 2 | Explore image segmentation with U-Net for a small portion of Carvana dataset
Day 13 Part 2 | Explore image segmentation with U-Net for a small portion of Carvana dataset
Day 13 Part 1 | Explore image segmentation with U-Net for a small portion of Carvana dataset
Day 13 Part 1 | Explore image segmentation with U-Net for a small portion of Carvana dataset
Day 10 | Use pre-built data augmentation methods in Keras on Fashion MNIST
Day 10 | Use pre-built data augmentation methods in Keras on Fashion MNIST
Day 9 | Modify CNN with pooling layers and visualize filters
Day 9 | Modify CNN with pooling layers and visualize filters
Day 8 | Build a simple CNN for CIFAR-10 image classification
Day 8 | Build a simple CNN for CIFAR-10 image classification
Day 7 | Fine-tune hyperparameters with Keras Tuner on a small NN
Day 7 | Fine-tune hyperparameters with Keras Tuner on a small NN