What is deep-learning?

A guide to building and training deep-learning models with Keras 3, a Python library for neural networks. It covers data preparation, model design, training, evaluation, and several model types and backends.

Use it to build computer-vision CNNs, language RNNs or Transformers, time-series forecasts, generative models, and other neural networks with JAX, TensorFlow, or PyTorch.

It provides a structured reference for common deep-learning tasks and helps choose among Keras's Sequential, Functional, and subclassing approaches. It also explains workflows for preparing and evaluating data.

deep-learning — Skill for Claude Code by Aznatkoiny: A guide to building and training deep-learning models with…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/aznatkoiny/zai-skills/deep-learning

Any agent

npx skills add Aznatkoiny/zAI-Skills --skill deep-learning

Clone the repo

git clone --depth 1 https://github.com/Aznatkoiny/zAI-Skills

Made for: Claude Code.

Or install ai-toolkit, the plugin that ships this one along with the rest of its 6 skills, 4 commands, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aznatkoiny/zai-skills/deep-learning.svg)](https://agentmods.dev/skills/aznatkoiny/zai-skills/deep-learning)

Your own site

<a href="https://agentmods.dev/skills/aznatkoiny/zai-skills/deep-learning"><img src="https://agentmods.dev/badge/skills/aznatkoiny/zai-skills/deep-learning.svg" alt="Measured on agentmods" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,022 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00091	$0.01022
Opus 5	$0.00046	$0.00511
Sonnet 5	$0.00018	$0.00204
Haiku 4.5	$0.00009	$0.00102

Measured 6d ago against content hash 8f5e322cb689, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deep-learning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/quick_train.py, scripts/visualize_filters.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AI-Toolkit/skills/deep-learning/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Learning with Keras 3

Patterns and best practices based on Deep Learning with Python, 2nd Edition by François Chollet, updated for Keras 3 (Multi-Backend).

Core Workflow

Prepare Data: Normalize, split train/val/test, create tf.data.Dataset
Build Model: Sequential, Functional, or Subclassing API
Compile: model.compile(optimizer, loss, metrics)
Train: model.fit(data, epochs, validation_data, callbacks)
Evaluate: model.evaluate(test_data)

Model Building APIs

Sequential - Simple stack of layers:

model = keras.Sequential([
    layers.Dense(64, activation="relu"),
    layers.Dense(10, activation="softmax")
])

Functional - Multi-input/output, shared layers, non-linear topologies:

inputs = keras.Input(shape=(64,))
x = layers.Dense(64, activation="relu")(inputs)
outputs = layers.Dense(10, activation="softmax")(x)
model = keras.Model(inputs=inputs, outputs=outputs)

Subclassing - Full flexibility with call() method:

class MyModel(keras.Model):
    def __init__(self):
        super().__init__()
        self.dense1 = layers.Dense(64, activation="relu")
        self.dense2 = layers.Dense(10, activation="softmax")

    def call(self, inputs):
        x = self.dense1(inputs)
        return self.dense2(x)

Quick Reference: Loss & Optimizer Selection

Task	Loss	Final Activation
Binary classification	`binary_crossentropy`	`sigmoid`
Multiclass (one-hot)	`categorical_crossentropy`	`softmax`
Multiclass (integers)	`sparse_categorical_crossentropy`	`softmax`
Regression	`mse` or `mae`	None

Optimizers: rmsprop (default), adam (popular), sgd (with momentum for fine-tuning)

Domain-Specific Guides

Topic	Reference	When to Use
Keras 3 Migration	keras3_changes.md	START HERE: Multi-backend setup, `keras.ops`, `import keras`
Fundamentals	basics.md	Overfitting, regularization, data prep, K-fold validation
Keras Deep Dive	keras_working.md	Custom metrics, callbacks, training loops, `tf.function`
Computer Vision	computer_vision.md	Convnets, data augmentation, transfer learning
Advanced CV	advanced_cv.md	Segmentation, ResNets, Xception, Grad-CAM
Time Series	timeseries.md	RNNs (LSTM/GRU), 1D convnets, forecasting
NLP & Transformers	nlp_transformers.md	Text processing, embeddings, Transformer encoder/decoder
Generative DL	generative_dl.md	Text generation, VAEs, GANs, style transfer
Best Practices	best_practices.md	KerasTuner, mixed precision, multi-GPU, TPU

Read the full file on GitHub · 91 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 91 lines · 91 tokens per session scan A 8f5e322cb689

Subscribe to this mod's changes

deep-learning is a skill published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,022 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI ai-tools anthropic claude-code claude-code-plugin consulting deep-learning

meta-prompting

Enhanced reasoning patterns via slash commands (/think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade) or natural language ("argue against", "what could break", "show reasoning", "deep review", "meta-prompts", "thinking modes"…

iliaal/whetstone · 104 tokens

refine-prompt

Transforms vague or rough prompts into precise, structured AI instructions. Use when asked to "refine prompt", "improve prompt", "make this prompt better", "promptify", "optimize prompt", "rewrite prompt", "enhance prompt", or "sharpen instructions".

iliaal/whetstone · 62 tokens

dataset-profiling

Use as the FIRST step of any ML task, before choosing a model, to inspect and understand the actual dataset. Works for a LOCAL dataset (Claude reads the files directly) and for a KAGGLE dataset (Claude cannot read /kaggle/input from your machine, so it emits a small profiling cell you run on Kaggle and paste back, or…

mxslr/mlcraft · 150 tokens

data-rigor-and-leakage

Use BEFORE training any model, to build correct train/val/test splits and hunt data leakage - the #1 cause of fake-high accuracy. Covers group/patient/subject splits, temporal splits, official-benchmark splits, label correctness, class balance, and preprocessing parity. Triggers on 'split the data', 'train/test…

mxslr/mlcraft · 96 tokens

grok-prompting

Internal guidance for composing Grok prompts for coding, review, diagnosis, and research tasks inside the Grok Claude Code plugin.

LovelaceLoom/grok-plugin-cc · 30 tokens

ml-research-methodology

Use at the START of ANY machine-learning / deep-learning / AI modeling task - building, training, fine-tuning, or choosing a model for image classification, object/face/vehicle detection, segmentation, medical imaging (tumor/cancer/MRI/X-ray/mammogram), text/NLP/LLM, tabular prediction (churn, price, risk), or…

mxslr/mlcraft · 127 tokens