Thanks to @emileifrem
, @bobvanluijt and others for talking about the future of graph databases and knowledge graph traversal in RAG pipelines! Lots more to talk about here but if you’re a company/dev experimenting with it would love to chat with you.
CODE
-
Graph Databases and Knowledge Graphs in RAG Pipelines
By
–
-
Managing Special Tokens in AI Models: Guidance Gaps
By
–
Has anyone seen published guidance about how to avoid tokens (including special things like [INST] or ) messing things up, for any of the available models? I've not seen good documentation on this myself yet
-
LangSmith Achieves 30% Accuracy Improvement Without Prompt Engineering
By
–
How Dosu used LangSmith to achieve a 30% accuracy improvement with no prompt engineering One of the goals of LangSmith is to help teams set up a data flywheel. By capturing LLM outputs alongside user feedback, we can help developers automatically use that feedback to improve
-
Daily Content on Python, Data Science, and Machine Learning
By
–
That's a wrap! If you are interested in any of these below topics: – Python – Data Science – Machine Learning – Data Analysis – LLMs – MLOps Find me → @Sumanth_077 I'm sharing daily content over here.
-
Single Forward Pass Network Prediction Implementation
By
–
Finally the Predict Function Now to predict on any new data all we need to do is a single Forward Pass through the Network:
-
Method to Train Neural Networks: Forward Pass, Backward Pass, Weight Updates
By
–
Now a method to train the neural network using both the forward and backward passes. The function will run for specified no of epochs, calculating: 1. The Forward Pass
2. Backward Pass
3. Updating the Weights -
Learning Rate Impact on Weight Updates in Neural Networks
By
–
Now Update the Weights: Here learning rate is the hyper parameter! A low learning rate can cause the model getting caught in local optima, while the high learning rate can cause the model to overshoot the general solution W1 += learning_rate * d_W1
b1 += learning_rate * d_b1 -
Calculate Gradients dW1 d_b2 d_b1 for Neural Network Backpropagation
By
–
Similarly calculate d_W1, d_b2 & d_b1 dW1: Gradient of the loss function wrt W1 d_b2: Gradient of the loss function wrt b2(bias of neuron in output layer) d_b1: Gradient of the loss function wrt b1(bias of neuron in hidden layer)
-
Neural Network Implementation From Scratch in Python
By
–
Neural Network implemented from scratch in Python (step-by-step explanation with code):
-
Building a Simple 2-Layer Neural Network with Sigmoid Activation
By
–
Below is the simple Neural Network consists of 2 layers: – Hidden Layer
– Output Layer First Initialize the size of layers along with the weights & biases. And also define the sigmoid activation function & it's derivative which is really key to introduce non-linearity.