Introduction to Machine Learning

Explore How AI Agents Navigate Driving Directions
1 Introduction
2 What is Artificial Intelligence
3 Grand Search Auto
4 Explore the Frontier
5 Depth-First Search
6 Breadth-First Search
7 Greedy-Best First and A Search

Apply Probability to Real-World AI Problems
8 Introduction
9 Probability of Rolling One 6-sided Die
10 Die Roll Simulation
11 Die Roll Probabilities
12 Probability of Rolling Two 6-sided Dice
13 Probability Distribution of Rolling Two 6-sided Dice

Define What is Machine Learning
14 Introduction
15 What is Machine Learning
16 What is Machine Learning
17 Unsupervised
18 Build an Image Classifier
19 Predicting Lumber Prices with Linear Regression

Setup a Machine Learning Development Environment
20 Introduction
21 Locally
22 Starting and Ending a Session
23 Google Colab
24 Cloud Services AWS, GCP, and Azure
25 Vast.ai the market leader in low-cost cloud GPU rental

Explore Data Pipelines and Linear Regression
26 Introduction
27 What is a Machine Learning Model
28 Predicting Lumber Prices Data Collection
29 Predicting Lumber Prices Data Cleaning & Preprocessing
30 Predicting Lumber Prices Feature Extraction

Apply Regression Concepts for Supervised Learning
31 Introduction
32 A Brief and Bizarre History of Linear Regression
33 Explore Linear Relationships Ordinary Least Squares
34 Seaborn Line of Best Fit
35 Ordinary Least Squares with Matlab’s PolyFit
36 Challenge

Examine Cost Functions and Parameter Tuning
37 Introduction
38 Mean Absolute Error
39 Mean Squared Error
40 Root Mean Squared Error
41 Cost Functions
42 Calculate Your Model’s Performance

Implement Gradient Descent for Linear Regression
43 Introduction
44 Exploring Gradient Descent Concepts
45 Exploring The Gradient Descent Algorithm
46 Gradient Descent Behind the Scenes
47 Implementing The Gradient Descent Algorithm

Vectorize Operations for Multiple Regression
48 Introduction
49 Multiple Linear Regression
50 Vectorization
51 Implementation Video
52 Non-Vectorized Operations
53 Interpreting the Weights

Explore Feature Engineering and Data Preparation
54 Introduction
55 What is Feature Engineering
56 Handling Missing Data
57 Handling Outliers
58 One Hot Encoding
59 Define, Split and Scale Features
60 Measuring Survival Accuracy

Identify Key Classification Algorithms
61 Introduction
62 From Regression to Classification
63 Logistic Regression
64 Decision Trees
65 Random Forests
66 Support Vector Machines
67 Perceptrons

Implement Logistic Regression with Python
68 Introduction
69 What is Logistic Regression
70 The Sigmoid Formula and Function
71 Logistic Regression in 4 lines of Code
72 Implement Logistic Regression – Part 1 Data Preprocessing, Cleaning, and Encoding
73 Part 2 Implement Logistic Regression and Measure Performance

Build a Python Decision Tree Classification Model
74 Introduction
75 Concepts Video
76 Entropy, Information Gain, and Gini Impurity
77 Import Libraries, Feature Engineering and One-Hot Encoding
78 Train, Test, Predict, and Measure Model Performance

Build a Python Random Forest Classification Model
79 Introduction
80 What is a Random Forest
81 Random Forest Concepts
82 Import Libraries, Feature Engineering and One-Hot Encoding
83 Train, Test, Predict, and Measure Model Performance
84 Bonus Hyperparameter Tuning Video

Apply Regularization to Overcome Overfitting
85 Introduction
86 What is Overfitting
87 Three Options for Handling Overfitting
88 Overfitting for Classification
89 Comparing Cost Functions
90 Perform Logistic Regression with Regularization

Build a Support Vector Machine Classifier
91 Introduction
92 What is a Support Vector Machine
93 Optimal Hyperplanes and the Margin
94 Data Loading and PreProcessing
95 Build and Evaluate the Model
96 Breast Cancer Wisconsin (Diagnostic) Dataset

Build a K-Nearest Neighbors Classifier
97 Introduction
98 What is K-Nearest Neighbors
99 KNN vs. Other Classifiers
100 What is Imbalanced Data
101 Data Loading and EDA
102 Data PreProcessing
103 Build and Evaluate the Model

Explore Neural Network Basics With The Perceptron
104 Introduction
105 Neurons as the building blocks of neural networks
106 Perceptrons As Artificial Neurons
107 How Activation Functions Work
108 Why Linearly Separable Data Is Key
109 Build A Simple Binary Perceptron Classifier
110 Challenge Complete The Perceptron Function
111 Solution Video

Implement a Perceptron for Classification
112 Introduction
113 What is a Perceptron
114 The Perceptron Rule and Neurons
115 Implement a Perceptron from Scratch
116 The Perceptron Challenge
117 Solution Video
118 Bonus Resources

Explore PyTorch Fundamentals for Machine Learning
119 Introduction
120 What Is PyTorch and Why It Is Useful
121 Set up a PyTorch Development Environment
122 Leverage Tensors Concepts
123 Leverage Tensors Programmatically
124 Challenge

Leverage PyTorch Tensor Attributes and Operators
125 Introduction
126 Tensor attributes
127 Tensor Math Operators
128 Matrix Multiplication
129 The PyTorch Double Challenge

Explore Fundamental PyTorch Tensor Operations
130 Introduction
131 Review Matrix Multiplication Errors
132 Min, Max, Mean, and Sum (Tensor Aggregation)
133 Navigating Positional Min Max Values
134 The Challenge
135 Solution Video
136 Bonus Resources

Apply PyTorch Tensor Manipulation and Indexing
137 Introduction
138 Reshape, View, and Stack Tensors
139 Squeeze and Unsqueeze Tensors
140 Permute Tensors
141 Index Tensors
142 Challenge Tensor Transformer
143 Solution Video

Explore Gradient Descent & Back Propagation
144 Introduction
145 Gradient Descent
146 Forward Propagation
147 Back Propagation
148 Training, Validation, and Test Datasets
149 Split The Train Test Datasets
150 Build a Linear Regression Model

Predict Ice Cream Sales with PyTorch Regression
151 Introduction
152 Device Agnostic Conditions & Load Data
153 Pre-Processing
154 Model Building
155 Mini-Challenge Model Training & Model Evaluation
156 Saving and Loading PyTorch Models
157 Challenge

Implement a Logistic Regression Model with PyTorch
158 Introduction
159 Review Sklearn Titanic Classification
160 Perform PyTorch Titanic Classification – Part1 Import Libraries, Define Model. and Load the data
161 Perform PyTorch Titanic Classification – Part2 Build model
162 Part 3 Fit model
163 Challenge – Part 1 Evaluate the Model
164 Part 3 Bonus Self-Graded Take-Home Challenge

Explore Neural Network Classification with PyTorch
165 Introduction
166 Review Logistic Regression PyTorch Workflow
167 Load Make Moons Dataset & Pre-processing
168 Define Neural Network Architecture
169 Train and Evaluate Model
170 Visualize Decision Boundary with Probability
171 Challenge PyTorch Workflow

Build a PyTorch Classifier with Non-Linearity
172 Introduction
173 Review Neural Network Classification Without Non-Linearity
174 Build a Neural Network Classification With Non-Linearity – Step 1 Load Dataset, Pre-processing, and Make Circles
175 Build a Neural Network Classification With Non-Linearity – Step 2 Define Neural Network Architecture
176 Step 3 Add Non-Linear Activation Function ReLu
177 Step 4 Train Model
178 Step 5 Evaluate Model
179 Challenge PyTorch Workflows

Explore Multi-class Classification with PyTorch
180 Introduction
181 Review of Binary Classification with PyTorch
182 Step 1 Setup and Prepare Data
183 Step 2 Visualize Data (EDA)
184 Step 3 Define Neural Network Architecture
185 Challenge
186 Solution Videos – Training Loop
187 Solution Video – Evaluation and Decision Boundary

Tune Hyperparameters and Analyze Fit with PyTorch
188 Introduction
189 Review Explore Multi-class Classification with PyTorch
190 Create, Preprocess, and Visualize the Spiral Dataset
191 Define Neural Network Architecture
192 Explore Hyperparameter Tuning
193 Explore Underfitting and Overfitting
194 Challenge
195 Solution Video

Discover What’s New with PyTorch 2.0
196 Introduction
197 Universal Device Setup in PyTorch 2.0
198 Key Features of PyTorch 2.0
199 Traditional PyTorch 1.0 Vs PyTorch 2.0 torch.compile( )
200 Challenge
201 Challenge Part 2

Explore TensorFlow Machine Learning Foundations
202 Introduction
203 Introduction to TensorFlow Tensors
204 Part 2
205 Create Tensors with TensorFlow
206 Create Random Tensors with Numpy
207 Challenge

Explore TensorFlow Aggregation and Manipulation
208 Introduction
209 Why Shuffle Tensors
210 TensorFlow Seeds
211 Tensor Attributes
212 Tensor Indexing
213 Changing Tensor Data Types & Tensor Aggregation
214 Tensor Positional Methods
215 Challenge
216 Challenge Part 2

Implement Matrix Multiplication with TensorFlow
217 Introduction
218 Basic Tensor Operation
219 TensorFlow Math Functions
220 Matrix Multiplication Foundations
221 Perform Matrix Multiplication
222 Challenge

Reshape, Transpose, and Alter TensorFlow Tensors
223 Introduction
224 Review Matrix Multiplication
225 Altering Tensors
226 Transpose & Reshape Tensors
227 Tensor Expansion
228 Challenge
229 Part 1
230 Part 2

Squeeze, Encode, and Optimize TensorFlow Tensors
231 Introduction
232 Squeezing Tensors
233 One-Hot Encoding
234 Numpy = Friend
235 GPU & TPU Tensor Optimization
236 Challenge
237 Challenge part 2

Explore Neural Network Regression with TensorFlow
238 Introduction
239 What is Regression Analysis
240 Neural Network Architecture
241 Build a Model
242 Challenge
243 Solution Video

Build a Simple Regression Model with TensorFlow
244 Introduction
245 Build a Small Regression Model from Memory
246 Build Model From Scratch
247 Challenge Improve Model
248 Solution Part 1
249 Solution Part 2

Evaluate Regression Models with TensorFlow
250 Introduction
251 Regression Challenge
252 Preprocess Data
253 Challenge Build Model
254 Challenge Solution

Visualize and Evaluate Performance with TensorFlow
255 Introduction
256 Generate Linear Transformation Data
257 Common Evaluation Metrics MAE, MSE, & Huber
258 Split Data for Train and Test Datasets
259 Define Basic Model Architecture
260 Make Predictions and Evaluate Model
261 Challenge
262 Solution Video

Normalize and Feature Scale Data with TensorFlow
263 Introduction
264 Handle Imports & Load Dataset
265 One-hot Encode & Separate Features and Target
266 Perform TrainTest Split
267 Define Model Architecture
268 Evaluate Model and Visualize Loss
269 What is Normalization and Standardization
270 Challenge
271 Solution Video

Explore TensorFlow Neural Network Classification
272 Introduction
273 What is Classification
274 What is Binary Classification
275 What is Multi-Class Classification
276 What is Multi-Label Classification
277 Classification Code Example
278 Challenge
279 Solution

Build a Neural Network Classifier with TensorFlow
280 Introduction
281 Pseudocode Image Classification
282 Create Circles Dataset & EDA
283 Build, Compile, and Train Model
284 Visualize and Evaluate Model
285 Challenge
286 Solution Video
287 Bonus Video

Build a TensorFlow Classifier with Non-Linearity
288 Introduction
289 Create Circles DataSet
290 Create Second Model
291 Create Third Model
292 Create Fourth Model
293 Challenge
294 Solution

Evaluate TensorFlow Classification Models
295 Review Learning Rates
296 Adaptive Learning Rates Part 1
297 Part 2
298 Part 3
299 Big Five Evaluation Metrics
300 Solution Video

Explore Multi-Class Classification with TensorFlow
301 Compare Binary and Multi-Class Classification
302 Create a Teachable Machine Multi-Class Classifier
303 Review Model Building Steps
304 Load and Explore MNIST Fashion Dataset
305 Challenge
306 Solution Video

Tune Multi-Class Classification TensorFlow Models
307 Introduction
308 Review MNIST Fashion Multi-Class Classifie
309 Load and Visualize Dataset
310 One-Hot Encode Features and Build Model
311 Softmax and Validation Exploration
312 Challenge
313 Solution Video

Explore Multi-Label Classification with TensorFlow
314 Introduction
315 Binary, Multi-Class, and Multi-Label Classification
316 Start Building a Multi-Label Classifier
317 Build a Sequential Multi-Label Model
318 Evaluate Model
319 Challenge
320 Solution Video

Explore The Fundamentals of Large Language Models
321 Introduction
322 What is a Large Language Model (LLM)
323 How do LLMs work
324 Two Kinds of LLMs Base and Instruction Tuned
325 System Messages and Tokens
326 System Messages and Tokens Part 2
327 Challenge Connect Google Colab to ChatGPT via OpenAI’s API

Build LLM Apps with ChatGPT and the OpenAI API
328 Introduction
329 Web Chat Interfaces Vs. Programmatic Notebooks
330 Route Queries Using Classification for Different Cases
331 Evaluate Inputs to Prevent Prompt Injections
332 Implement The OpenAI Moderation API
333 Sanitize and Validate Inputs Injection Attacks
334 Challenge Filter Inputs with a Chain of Thought Prompt Filter

Design Effective Prompts for Large Language Models
335 Introduction
336 Iterative Prompt Engineering
337 Build a Summarizer for Interesting Topics
338 Implement Supervised Learning Through Inference
339 Challenge Build The AutoBot ChatBot To Manage Orders

Implement LangChain in Language Model Workflows
340 Introduction
341 Compare Direct API Calls Vs. API Calls Through LangChain
342 Leverage LangChain Templating for Complex Prompts
343 Leverage Power of Templating for DRY Code
344 Challenge
345 Solution

Implement LangChain Memory for Autonomous Tasks
346 Introduction
347 ConversationBufferMemory
348 ConversationBufferWindowMemory
349 ConversationTokenBufferMemory
350 ConversationSummaryBufferMemory
351 The Power of Chaining LangChain Components
352 Challenge Implement LangChain Memory

Challenge Implement LangChain Memory
353 Introduction
354 Chaining in LangChain
355 LLMChain
356 SimpleSequentialChain
357 SequentialChain
358 RouterChain
359 Challenge

Build Task-Driven Autonomous Agents with LangChain
360 Introduction
361 Leverage LangChain Agents
362 Perform math calculation using an Math LLM
363 Use Wikipedia to Find General Information
364 Program using a Python REPL tool
365 Create new custom agents and tooling (BabyAGI)
366 Debugging with LangChain
367 Challenge

Use LangChain to Interact with PDFs and Documents
368 Introduction
369 Retrieval Augmented Generation (RAG) over 2 Skills
370 Document Loaders
371 Document Separation
372 Embeddings
373 Vector Stores

Use LangChain to Chat with PDFs and Documents
374 Introduction
375 Similarity Search
376 Maximum Margin Relevance
377 ContextualCompressionRetriever + MMR
378 Chat Q&A
379 Chat Q&A Part 2
380 Challenge

Explore Transformer Encoders and Decoders
381 Introduction
382 What are Transformers
383 Attention Is All You Need (Optional)
384 Encoders
385 Decoders
386 Encoder-Decoders
387 What is HuggingFace Again

Examine the Fundamentals of HuggingFace
388 Introduction
389 What is HuggingFace
390 Models
391 Datasets
392 Spaces
393 ChatGPT Competitor HuggingChat
394 Challenge