Best of Deep Learning — May 2024

1. 1
   Article

   freeCodeCamp·2y

   Deep Learning Course – Math and Applications

   Learn the math behind deep learning with a 14-hour course on the freeCodeCamp YouTube channel. Developed by Ayush Singh, the course covers fundamental concepts, deep learning techniques, mathematical insights, and practical applications. Topics include vectors, matrices, linear algebra, calculus, machine learning, and neural networks.

   117

   1
2. 2
   Article

   GoPenAI·2y

   How to build Neural Network with real-world dataset using PyTorch

   Learn how to build and train a neural network model using the FitBit Fitness Tracker Dataset and PyTorch. The post provides a step-by-step guide and covers topics such as importing libraries, loading and preparing the data, defining the model, training and evaluating the model, and making predictions on new data. By following the post, readers can build and train their own neural network models for various use cases.

   52
3. 3
   Article

   Daily Dose of Data Science | Avi Chawla | Substack·2y

   Transfer Learning, Fine-tuning, Multitask Learning and Federated Learning

   Learn about transfer learning, fine-tuning, multitask learning, and federated learning in ML modeling.

   22
4. 4
   Article

   KDnuggets·2y

   The Best Strategies for Fine-Tuning Large Language Models

   Learn how to fine-tune large language models for specialized tasks and customize them to suit specific requirements.

   17
5. 5
   Article

   The Palindrome·2y

   Understanding k-Nearest Neighbors

   kNN is a lazy machine learning algorithm that doesn't require training. It makes predictions by calculating distances between new samples and training samples, finding the k nearest neighbors, and classifying the new sample based on a majority vote from those neighbors. The value of 'k' is important as it determines the number of samples considered for prediction. The choice of 'k' can have a significant impact on the outcome. Different distance metrics, such as Euclidean distance, Manhattan distance, and Minkowski distance, can be used in kNN depending on the problem. Cosine similarity is another distance metric that can be useful for high-dimensional data.

   17
6. 6
   Article

   GoPenAI·2y

   Fine-Tuning Llama in practices

   This blog post provides practical tips on fine-tuning Llama-2 models, including methods like LoRA and QLoRA that reduce memory requirements while maintaining performance. It also guides readers through the fine-tuning process with code examples.

   16
7. 7
   Article

   Medium·2y

   How to fine-tune an Mistral7b LLM on custom dataset, with QLoRA, PEFT following MLOps practices

   The LLM Twin course teaches you how to design, train, and deploy a production-ready LLM twin using LLMs, vector DBs, and MLOps best practices. It covers the fine-tuning of LLMs on custom datasets at scale using Qwak and CometML.

   14
8. 8
   Article

   Medium·2y

   Top DevTools to Build AI/ML Applications!

   Discover the top DevTools for building AI/ML applications, from programming languages like Wing to vector data storage with SingleStore, and data manipulation with Pandas and NumPy.

   12
9. 9
   Article

   BAIR·2y

   TinyAgent: Function Calling at the Edge

   TinyAgent is a small language model (SLM) that can perform complex reasoning and function calling. It can be deployed locally at the edge, reducing the need for cloud connectivity and ensuring privacy. TinyAgent achieves improved function calling performance through fine-tuning on a specialized dataset and the use of Tool RAG for efficient tool selection based on user queries. The model can also be quantized to further reduce latency and model size.

   10