Onbetrouwbare gegevensbron identificeren

Je team ontwikkelt een model om te helpen bij het genereren van nauwkeurige rapportages in de auto-veiligheidsindustrie. Je hebt voorkeursdata verzameld uit drie gegevensbronnen: een "GlobalDrive Safety Institute", een "AutoTech Safety Alliance" en "QuickScan Auto Review". Onlangs zijn er zorgen ontstaan over de integriteit van de data, en je bent gevraagd om te beoordelen of er onbetrouwbare gegevensbronnen zijn.

automotive_df is een gecombineerde DataFrame die is geladen met de voorgeïmporteerde pandas-bibliotheek. Het bevat data van de drie bronnen. De voorgeïmporteerde functie majority_vote maakt een dictionary-achtig object met het meerderheidspaar (chosen, rejected) per 'id'.

Deze oefening maakt deel uit van de cursus

Reinforcement Learning from Human Feedback (RLHF)

Cursus bekijken

Oefeninstructies

Definieer de voorwaarde om één onenigheid met de meerderheidstem te tellen voor een gegeven gegevensbron.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

def detect_unreliable_source(merged_df):
    df_majority = df.groupby('id').apply(majority_vote)
    disagreements = {source: 0 for source in df['source'].unique()}
    for _, row in df.iterrows():
        # Condition to find a disagreement with majority vote
        ____
    unreliable_source = max(disagreements, key=disagreements.get)
    return unreliable_source

disagreement = detect_unreliable_source(automotive_df)
print("Unreliable Source:", disagreement)

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Reinforcement Learning from Human Feedback (RLHF)

SkillTag.level.advancedSkillTag.label

4.8+

Begin de cursus gratis

This chapter introduces the basics of Reinforcement Learning with Human Feedback (RLHF), a technique that uses human input to help AI models learn more effectively. Get started with RLHF by understanding how it differs from traditional reinforcement learning and why human feedback can enhance AI performance in various domains.

Exercise 1: Introduction to RLHF Exercise 2: Text generation with RLHF Exercise 3: Classifying generated text for RLHF Exercise 4: RL vs. RLHF Exercise 5: Exploring pre-trained LLMs Exercise 6: Tokenize a text dataset Exercise 7: Fine-tuning for review classification Exercise 8: Preparing data for RLHF Exercise 9: Preparing the preference dataset Exercise 10: Extracting prompts

Discover how to set up systems for gathering human feedback in this Chapter. Learn best practices for collecting high-quality data, from pairwise comparisons to uncertainty sampling, and explore strategies for enhancing your data collection.

Exercise 1: Methods for high-quality feedback gathering Exercise 2: Understanding comparison and rating in RLHF Exercise 3: Comparing slogans for a gym campaign Exercise 4: Measuring feedback quality and relevance Exercise 5: Low confidence Exercise 6: K-means for feedback clustering Exercise 7: Active learning Exercise 8: Implementing an active learning pipeline Exercise 9: Active learning loop

In this Chapter, you'll get into the core of Reinforcement Learning from Human Feedback training. This includes exploring fine-tuning with PPO, techniques to train efficiently, and handling potential divergences from your metrics' objectives.

Exercise 1: Reward models explored Exercise 2: Initializing the reward Exercise 3: Setting up the reward trainer Exercise 4: Training with PPO Exercise 5: Initialize the PPO trainer Exercise 6: PPO fine-tuning Exercise 7: Efficient fine-tuning in RLHF Exercise 8: Prepare for 8-bit Training Exercise 9: Train with LoRA

Explore key techniques for assessing and improving model performance in this last Chapter of Reinforcement Learning from Human Feedback (RLHF): from fine-tuning metrics to incorporating diverse feedback sources, you'll be provided with a comprehensive toolkit to refine your models effectively.

Exercise 1: Modelmetingen en bijsturing Exercise 2: Negatieve KL-divergentie beperken Exercise 3: Het rewardmodel controleren Exercise 4: Diverse feedbackbronnen integreren Exercise 5: Meerderheidsstemming over meerdere databronnen Exercise 6: Onbetrouwbare gegevensbron identificeren

Huidige oefening

Exercise 7: RLHF-modellen evalueren Exercise 8: Curves interpreteren Exercise 9: RLHF evalueren met metriek Exercise 10: Afronding van je RLHF-reis