Skip to content
tezvyn:

All bites

The whole library, newest first. Filter by what you are here for, or pick a topic if you already know.

4330 bites

Page 158

How do you leverage and fine-tune BERT for niche classification?
Data Science & Analytics2 min read

How do you leverage and fine-tune BERT for niche classification?

Tests transfer learning with scarce labels. Outline: pick a domain-adjacent checkpoint, add a classification head, use learning rates near 2e-5 with early stopping, and stratify tiny validation splits.

Data Science & Analytics2 min read

RL components and how Q-learning works

Agent acts on the environment, observes state and reward, seeking to maximize cumulative discounted reward; Q-learning iteratively updates Q(s,a) toward reward plus discounted best…

Data Science & Analytics2 min read

Walk me through a CNN's layers for image classification

Tests hierarchical feature extraction in CNNs. Answer: conv filters learn edges-to-objects with shared weights, pooling reduces dimensions and adds invariance, fully-connected layers classify.

Data Science & Analytics2 min read

Exploration versus exploitation: epsilon-greedy and UCB

Exploit current best to earn reward, explore to discover better options; epsilon-greedy explores randomly with probability epsilon; UCB explores by an uncertainty bonus…

Data Science & Analytics1 min read

Why Transformers use multi-head attention

A single head averages into one representation subspace; multiple heads attend in parallel to different subspaces, letting the model capture diverse relations like syntax and coreference at once, then…

Data Science & Analytics1 min read

Mode collapse in GANs and how to fix it

Mode collapse is the generator producing few similar outputs, missing data diversity to fool the discriminator; fixes include Wasserstein loss, minibatch discrimination, unrolled GANs, and feature…

Data Science & Analytics1 min read

Spark transformations versus actions

Transformations like map and filter are lazy and build a lineage DAG returning a new RDD; actions like count or collect trigger execution and return a value to the driver.

Data Science & Analytics1 min read

HDFS purpose and fault tolerance

HDFS stores huge files across many commodity machines as large blocks, replicating each block across nodes for fault tolerance; unlike NTFS or ext4 it is distributed, write-once, and optimized for…

Data Science & Analytics1 min read

The MapReduce paradigm explained

Map applies a function to each input record emitting key-value pairs in parallel; a shuffle groups values by key; reduce aggregates each key's values into a result.

Data Science & Analytics2 min read

Spark broadcast join versus shuffle join

A broadcast join sends the small table to every executor so the large table joins locally with no shuffle of its rows; the default sort-merge join shuffles both tables across the network, which is costly.

Data Science & Analytics2 min read

Data skew in Spark and salting

Data skew is uneven key distribution sending most rows to one partition and straggler task; salting appends a random suffix to hot keys to spread them across partitions, joining in two…

Data Science & Analytics1 min read

Spark RDDs, DataFrames, and Datasets

RDDs are low-level typed object collections with no built-in optimization; DataFrames are named columns optimized by Catalyst and Tungsten; Datasets add compile-time type safety in…

Data Science & Analytics2 min read

Diagnosing Spark executor OutOfMemoryError

Check the Spark UI for skew and spills, inspect executor memory and partition count, find culprits like wide collect, huge shuffles, or skewed keys, and fix via more partitions, memory tuning, or…

Data Science & Analytics1 min read

Visualizing long-term trend versus seasonality

A line chart over the full three years, often with a moving average, shows the long-term trend; a seasonal plot overlaying each year by month, or a month-of-year box plot, reveals…

Data Science & Analytics1 min read

Reconcile rising sign-ups with falling revenue per user

Reconcile the metrics via total revenue and segment mix, frame the tradeoff, recommend an action.

Data Science & Analytics1 min read

Two ways accurate data can still mislead in a chart

Name distortions like truncated axes or cherry-picked ranges, give the fix for each, explain why each misleads.

Data Science & Analytics1 min read

Explain k-means user segments to a marketing team

Name each segment, profile its defining traits, show size and value, recommend an action.

Data Science & Analytics1 min read

Deploy a saved model as a REST prediction service

Load the artifact, wrap it in a predict API, containerize, host with autoscaling, add monitoring.

Data Science & Analytics1 min read

Batch prediction versus online real-time prediction

Batch is scheduled bulk scoring, online is low-latency per-request scoring; contrast latency, freshness, cost; give a use case each.

Data Science & Analytics1 min read

Detecting and responding to model and concept drift

Define drift, pick a metric like PSI or falling AUC against labels, then investigate, retrain, validate.