Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit cc6bb5c

Browse files
shalmalijoshishalmalijoshi
committed
homework schedule and logistics updates
1 parent 1ab8927 commit cc6bb5c

File tree

1 file changed

+40
-40
lines changed

1 file changed

+40
-40
lines changed

‎binf4002.html‎

Lines changed: 40 additions & 40 deletions
Original file line numberDiff line numberDiff line change
@@ -26,18 +26,18 @@ <h4><u>Staff:</u></h4>
2626
<br>
2727

2828
<h4><u>Logistics:</u></h4>
29-
<b>Contact:</b> <a href="">Courseworks</a><br>
30-
<b>Time:</b> Tuesdays, Thursdays 9:00a - 10:15am<br>
29+
<b>Contact:</b> <a href="https://courseworks2.columbia.edu/courses/210430/">Courseworks</a><br>
3130
<b>Location:</b> 622 W 168th St, PH20-200, NY-10032 on the 20th floor of the Presybterian Hospital Building (<a href="https://www.cuimc.columbia.edu/about-us/explore-cuimc/campus-map-and-directions">Directions</a>)<br>
32-
<b>Instructor Office Hours:</b> Shalmali Joshi: Fridays 10:00a-11:00a at 622 W 168th St, PH-20, Room 402<br>
33-
<b>TA Recitation and Office Hours:</b> Young Sang Choi and Yuta Kobayashi: Fridays 10:30am-11:45am, at 622 W 168th St, PH-20-200<br>
31+
<b>Lecture Times:</b> Tuesdays, Thursdays 9:00a - 10:15am<br>
32+
<b>Instructor Office Hours:</b> Shalmali Joshi: Fridays TBD at 622 W 168th St, PH-20, 402<br>
33+
<b>TA Recitation and Office Hours (optional):</b> Young Sang Choi and Yuta Kobayashi: Fridays TBD, at 622 W 168th St, PH-20, Collaboration Room<br>
3434

3535
<br>
3636

3737

3838
<h4><u>Pre-reqs:</u></h4>
3939
<ul>
40-
<li>Basic knowledge of probability, statistics, and linear algebra is expected and required.</li>
40+
<li>Basic knowledge of probability, statistics, calculus, and linear algebra is expected and required.</li>
4141
<li>Familiarity with programming with Python and versioning systems like Git is required.</li>
4242

4343
</ul>
@@ -94,7 +94,7 @@ <h3>Schedule and Content</h3>
9494
<th>Day</th>
9595
<th>Topic</th>
9696
<th>Subtopics</th>
97-
<th>Reading Materials/References</th>
97+
<!--th>Reading Materials/References</th-->
9898
<th>Homework timelines</th>
9999
</tr>
100100
</thead>
@@ -105,7 +105,7 @@ <h3>Schedule and Content</h3>
105105
<td>Tuesday</td>
106106
<td>Intro and course logistics, MIMIC-IV access, Google Colab Credits</td>
107107
<td>Colab accounts setup, data downloads, conda environment setup, etc.</td>
108-
<td></td>
108+
<!--td></td-->
109109
<td>Homework 0 out with instructions on setting up Colab, accessing MIMIC-IV data</td>
110110
</tr>
111111
<tr>
@@ -114,7 +114,7 @@ <h3>Schedule and Content</h3>
114114
<td>Thursday</td>
115115
<td>Probability and information theory primer</td>
116116
<td></td>
117-
<td></td>
117+
<!--td></td-->
118118
<td>Homework 0 due, Homework 1 out</td>
119119
</tr>
120120
<tr>
@@ -123,7 +123,7 @@ <h3>Schedule and Content</h3>
123123
<td>Tuesday</td>
124124
<td>Linear algebra and optimization primer</td>
125125
<td></td>
126-
<td></td>
126+
<!--td></td-->
127127
<td></td>
128128
</tr>
129129
<tr>
@@ -132,7 +132,7 @@ <h3>Schedule and Content</h3>
132132
<td>Thursday</td>
133133
<td>Introduction to supervised learning</td>
134134
<td>Empirical Risk Minimization, Loss functions, Model families</td>
135-
<td></td>
135+
<!--td></td-->
136136
<td></td>
137137
</tr>
138138
<tr>
@@ -141,7 +141,7 @@ <h3>Schedule and Content</h3>
141141
<td>Tuesday</td>
142142
<td>Introduction to supervised learning</td>
143143
<td>IID vs OOD, Bias-variance tradeoff, regularization</td>
144-
<td></td>
144+
<!--td></td-->
145145
<td></td>
146146
</tr>
147147
<tr>
@@ -150,7 +150,7 @@ <h3>Schedule and Content</h3>
150150
<td>Thursday</td>
151151
<td>Empirical practices in machine learning</td>
152152
<td>LOOCV, validation data, calibration, uncertainty quantification, bootstrapping</td>
153-
<td></td>
153+
<!--td></td-->
154154
<td></td>
155155
</tr>
156156
<tr>
@@ -159,7 +159,7 @@ <h3>Schedule and Content</h3>
159159
<td>Tuesday</td>
160160
<td>Principles of Maximum Likelihood</td>
161161
<td>Logistic regression- two views, other models motivated by maximum likelihood estimation</td>
162-
<td></td>
162+
<!--td></td-->
163163
<td></td>
164164
</tr>
165165
<tr>
@@ -168,7 +168,7 @@ <h3>Schedule and Content</h3>
168168
<td>Thursday</td>
169169
<td>Basics of probabilistic modeling and Bayesian inference</td>
170170
<td>Prior, Likelihood, and Posterior. Logistic and Linear Regression</td>
171-
<td></td>
171+
<!--td></td-->
172172
<td></td>
173173
</tr>
174174
<tr>
@@ -177,7 +177,7 @@ <h3>Schedule and Content</h3>
177177
<td>Tuesday</td>
178178
<td>Basics of probabilistic modeling and Bayesian inference</td>
179179
<td>Posterior Predictive, Exponential Familities, Maximum-a-Posteriori</td>
180-
<td></td>
180+
<!--td></td-->
181181
<td>Homework 1 due, Homework 2 out</td>
182182
</tr>
183183
<tr>
@@ -186,7 +186,7 @@ <h3>Schedule and Content</h3>
186186
<td>Thursday</td>
187187
<td>Introduction to Regression</td>
188188
<td>Linear regression, other types of regression</td>
189-
<td></td>
189+
<!--td></td-->
190190
<td></td>
191191
</tr>
192192
<tr>
@@ -195,7 +195,7 @@ <h3>Schedule and Content</h3>
195195
<td>Tuesday</td>
196196
<td>Bayesian linear regression</td>
197197
<td>Derivation and connection to regularization</td>
198-
<td></td>
198+
<!--td></td-->
199199
<td></td>
200200
</tr>
201201
<tr>
@@ -204,7 +204,7 @@ <h3>Schedule and Content</h3>
204204
<td>Thursday</td>
205205
<td>Empirical practices in machine learning - revisited</td>
206206
<td>Comparing approaches to uncertainty quantification, best practices, etc.</td>
207-
<td></td>
207+
<!--td></td-->
208208
<td></td>
209209
</tr>
210210
<tr>
@@ -213,7 +213,7 @@ <h3>Schedule and Content</h3>
213213
<td>Tuesday</td>
214214
<td>Review of basic supervised learning</td>
215215
<td>Decision trees, Random Forests, XGBoost</td>
216-
<td></td>
216+
<!--td></td-->
217217
<td></td>
218218
</tr>
219219
<tr>
@@ -222,7 +222,7 @@ <h3>Schedule and Content</h3>
222222
<td>Thursday</td>
223223
<td>Introduction to deep neural networks</td>
224224
<td>Multilayer perceptron and connection to logistic and linear regression</td>
225-
<td></td>
225+
<!--td></td-->
226226
<td></td>
227227
</tr>
228228
<tr>
@@ -231,16 +231,16 @@ <h3>Schedule and Content</h3>
231231
<td>Tuesday</td>
232232
<td>Optimization in deep neural networks</td>
233233
<td>Backpropagation, stochastic gradient descent</td>
234-
<td></td>
235-
<td></td>
234+
<!--td></td-->
235+
<td>Homework 2 due, Homework 3 out</td>
236236
</tr>
237237
<tr>
238238
<td>16</td>
239239
<td>2024-03-13</td>
240240
<td>Thursday</td>
241241
<td>Midterm</td>
242242
<td>Midterm</td>
243-
<td></td>
243+
<!--td></td-->
244244
<td></td>
245245
</tr>
246246
<tr>
@@ -249,16 +249,16 @@ <h3>Schedule and Content</h3>
249249
<td>Tuesday</td>
250250
<td>Spring break</td>
251251
<td>Spring break</td>
252+
<!--td></td-->
252253
<td></td>
253-
<td>Homework 2 due, Homework 3 out</td>
254254
</tr>
255255
<tr>
256256
<td>No class</td>
257257
<td>2024-03-20</td>
258258
<td>Thursday</td>
259259
<td>Spring break</td>
260260
<td>Spring break</td>
261-
<td></td>
261+
<!--td></td-->
262262
<td></td>
263263
</tr>
264264
<tr>
@@ -267,7 +267,7 @@ <h3>Schedule and Content</h3>
267267
<td>Tuesday</td>
268268
<td>Deep learning for image data</td>
269269
<td>Convolutional Neural Networks</td>
270-
<td></td>
270+
<!--td></td-->
271271
<td></td>
272272
</tr>
273273
<tr>
@@ -276,7 +276,7 @@ <h3>Schedule and Content</h3>
276276
<td>Thursday</td>
277277
<td>Deep learning for sequential data</td>
278278
<td>Recurrent Neural Networks, LSTM, State-space models, Gated Recurrent Units</td>
279-
<td></td>
279+
<!--td></td-->
280280
<td></td>
281281
</tr>
282282
<tr>
@@ -285,7 +285,7 @@ <h3>Schedule and Content</h3>
285285
<td>Tuesday</td>
286286
<td>Deep learning for networked data</td>
287287
<td>Graph Neural Networks</td>
288-
<td></td>
288+
<!--td></td-->
289289
<td></td>
290290
</tr>
291291
<tr>
@@ -294,7 +294,7 @@ <h3>Schedule and Content</h3>
294294
<td>Thursday</td>
295295
<td>Deep learning for sequential data</td>
296296
<td>Transformer: Attention-based neural networks</td>
297-
<td></td>
297+
<!--td></td-->
298298
<td></td>
299299
</tr>
300300
<tr>
@@ -303,16 +303,16 @@ <h3>Schedule and Content</h3>
303303
<td>Tuesday</td>
304304
<td>Deep learning for sequential data - contd</td>
305305
<td>Training paradigms for sequence based models (e.g., Seq-2-seq, decoder-only etc)</td>
306-
<td></td>
307-
<td></td>
306+
<!--td></td-->
307+
<td>Homework 3 due, Homework 4 out</td>
308308
</tr>
309309
<tr>
310310
<td>22</td>
311311
<td>2024-04-10</td>
312312
<td>Thursday</td>
313313
<td>Distribution shifts, generalization, and domain adaptation</td>
314314
<td>Concept of generalization, types of distribution shifts, examples of implications in healthcare</td>
315-
<td></td>
315+
<!--td></td-->
316316
<td></td>
317317
</tr>
318318
<tr>
@@ -321,16 +321,16 @@ <h3>Schedule and Content</h3>
321321
<td>Tuesday</td>
322322
<td>Distribution shifts, generalization, and domain adaptation - contd.</td>
323323
<td>Focus on various methods of adaptation to overcome different types of distribution shifts</td>
324+
<!--td></td-->
324325
<td></td>
325-
<td>Homework 3 due, Homework 4 out</td>
326326
</tr>
327327
<tr>
328328
<td>24</td>
329329
<td>2024-04-17</td>
330330
<td>Thursday</td>
331331
<td>Unsupervised learning</td>
332332
<td>History and review of classical methods, brief review of modern methods</td>
333-
<td></td>
333+
<!--td></td-->
334334
<td></td>
335335
</tr>
336336
<tr>
@@ -339,7 +339,7 @@ <h3>Schedule and Content</h3>
339339
<td>Tuesday</td>
340340
<td>Generative modeling</td>
341341
<td>Foundations of generative model, basic loss-functions and a broad overview of models</td>
342-
<td></td>
342+
<!--td></td-->
343343
<td></td>
344344
</tr>
345345
<tr>
@@ -348,7 +348,7 @@ <h3>Schedule and Content</h3>
348348
<td>Thursday</td>
349349
<td>Foundation models -LLMs</td>
350350
<td>Large-language models (Transformers but more)</td>
351-
<td></td>
351+
<!--td></td-->
352352
<td></td>
353353
</tr>
354354
<tr>
@@ -357,7 +357,7 @@ <h3>Schedule and Content</h3>
357357
<td>Tuesday</td>
358358
<td>Foundation models - Vision-language</td>
359359
<td>CLIP and other basic Vision-language models</td>
360-
<td></td>
360+
<!--td></td-->
361361
<td>Homework 4 due</td>
362362
</tr>
363363
<tr>
@@ -366,7 +366,7 @@ <h3>Schedule and Content</h3>
366366
<td>Thursday</td>
367367
<td>Foundation models- Biological data - e.g., AlphaFold</td>
368368
<td>Major foundation models for biological data</td>
369-
<td></td>
369+
<!--td></td-->
370370
<td></td>
371371
</tr>
372372
<tr>
@@ -375,7 +375,7 @@ <h3>Schedule and Content</h3>
375375
<td>Monday</td>
376376
<td>Finals</td>
377377
<td></td>
378-
<td></td>
378+
<!--td></td-->
379379
<td></td>
380380
</tr>
381381
</tbody>
@@ -399,7 +399,7 @@ <h3>Homework Assignments (40 points)</h3>
399399
<a name="exams"></a>
400400
<h3>Exams</h3>
401401

402-
There will be one mid-term (25 points) and one final exam (30 points). Both exams will be for the duration of the class. You will be allowed one Letter sized cheat sheet for formulae only. You will return the cheat sheet along with the exam for grading.
402+
There will be one mid-term (25 points) and one final exam (30 points). Both exams will be for the duration of the class. You will be allowed one Letter-sized cheat sheet for formulae only. You will return the cheat sheet along with the exam for grading.
403403

404404
</body>
405405
</html>

0 commit comments

Comments
 (0)